Option D uses the established integration mechanism without creating unnecessary infrastructure. Anthropic's Claude Code MCP documentation specifically recommends connecting an MCP server when users repeatedly copy information from an external system, such as an issue tracker, into conversations. Once connected, the server exposes Jira operations through named, schema-defined tools that Claude can discover and invoke directly. This allows the agent to retrieve ticket descriptions, acceptance criteria, comments, and metadata while preserving the server's authentication and access controls.
Option A exposes authentication details to shell commands and requires the agent to construct requests and parse responses repeatedly. Option B is justified only when no existing server provides the required capabilities or the workflow requires highly specialized operations. The question requires standard Jira information, so building and maintaining another server is unnecessary. Option C creates stale, manually synchronized copies that lose permissions, current comments, and authoritative ticket state. The team should therefore select a trusted Jira MCP implementation, configure appropriate read-only scopes where possible, and verify its tool descriptions and data-access boundaries before enabling it.

Option A combines lossless persistence with selective restoration. Each agent should checkpoint structured records containing completed document identifiers, extracted findings, source provenance, unresolved work, verification status, and schema version. A coordinator-level manifest can record which stages completed and where their artifacts are stored. On recovery, the coordinator skips completed documents and injects only the state required by each restarted agent.
Anthropic's effective context-engineering guidance recommends structured notes stored outside the active context window and reloaded when needed. This preserves critical dependencies and progress without replaying an entire execution history.
Option B fragments recovery ownership across agents and makes cross-agent consistency, versioning, and dependency validation difficult. Option C preserves extensive logs but wastes context on redundant tool calls, obsolete instructions, and intermediate messages. Option D is useful for relevance retrieval but semantic search can omit exact details and should not serve as the authoritative recovery record. Structured checkpoints and a validated manifest provide deterministic recovery, efficient context reconstruction, auditability, and precise provenance. Writes should be atomic so partially produced exports are never mistaken for completed work.

Option B gives the report generator the two forms of information it actually needs: a compact narrative containing the synthesized conclusions and precise evidence records supporting those conclusions. The source index should map claim identifiers to URLs, document locations, excerpts, and other provenance fields so citations can be generated and verified without reloading 120,000 tokens of raw material.
Anthropic's context-engineering guidance recommends distilling extensive subagent activity into high-signal summaries while preserving critical context and dependencies. Its research architecture similarly treats subagents as intelligent filters that compress large evidence collections before returning relevant findings to the coordinator.
Option A lacks sufficient location-level evidence for reliable citation verification. Option C postpones attribution until after drafting, when claim wording may no longer map cleanly to the original evidence.
Option D maximizes theoretical completeness but introduces extensive irrelevant material, higher token costs, slower processing, and greater context pollution. The synthesis draft plus a structured claim-to-source index maintains evidentiary completeness where it matters while eliminating intermediate searches, duplicate passages, and other low-value context.

An aggregate accuracy value can conceal severe performance disparities. A system may achieve 97% overall accuracy while performing poorly on a low-volume document type, a critical financial field, or a specific edge case. Automating outputs solely from the aggregate figure could therefore expose downstream systems to concentrated, high-impact errors.
Anthropic's evaluation guidance states that evaluations should be task-specific, reflect the real-world task distribution, and explicitly include edge cases. It also emphasizes multidimensional success criteria rather than reliance on a single global metric. ( https://docs.anthropic.com/en/docs/build-with-claude/develop-tests ) Option A applies those principles by stratifying performance according to document type and field. This reveals whether confidence is calibrated consistently and whether the proposed automation threshold remains safe for every operationally significant segment.
Option B is useful only after segment-level performance has been understood. Selecting a global threshold cannot correct a subgroup where confidence is systematically overstated. Option C is necessary governance work, but it treats the overall 97% result as though errors were uniformly distributed. Option D places unvalidated outputs into downstream systems and depends on passive error reporting, which may fail to detect silent corruption.
The correct deployment gate is therefore segmented validation, followed by threshold selection, downstream acceptance criteria, and a controlled pilot.
Official references/topics: Define Success Criteria; Task-Specific Evaluations; Edge-Case Coverage; Reliability Segmentation.

Option C converts the linear pipeline into a controlled iterative research loop. The document-analysis agent is best positioned to identify precisely what the retrieved evidence fails to answer. It should return structured gaps containing the missing question, evidence already examined, preferred source characteristics, and the coverage criterion that remains unsatisfied. The coordinator can then issue focused searches and resubmit the new material for analysis.
Anthropic's multi-agent research architecture uses a lead agent to decompose work, coordinate research agents, assess returned information, and continue investigation when further evidence is required. The guidance also stresses clear objectives, output formats, source requirements, and task boundaries to prevent gaps and duplicated work.
Option A may improve initial coverage but cannot anticipate every deficiency revealed only after sources are examined. Option B documents incompleteness rather than correcting it. Option D retrieves more information but does not ensure that the new evidence is analyzed and tested against the original gap. The loop in Option C establishes an explicit completion condition and preserves specialization: analysis identifies the gap, the coordinator orchestrates, search agents retrieve evidence, and analysis verifies whether the gap has actually been closed.