export_draft_replay_package

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond annotations: the output is a deterministic replay package bundling provenance integrity, Registry support, optional artifact verification, and recent audit records. It does not state format, size, or determinism mechanics, but it goes meaningfully beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the core action first and details trailing. It is efficient and contains no filler, though the long comma-separated enumeration is dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter tool with an output schema, the description need not explain return values, and annotations cover safety. However, given the cluttered sibling namespace and 0% parameter documentation, it leaves gaps: no guidance on choosing between artifact_path and artifact_relative_path, no mention of the audit limit behavior, and no differentiation from adjacent export tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for six parameters, so the schema supplies only names and types. The description references 'one draft version', 'artifact verification', and 'recent MCP audit records', which loosely maps to draft_id/version_id, artifact_path/artifact_relative_path, and audit_record_limit/include_audit_records. But it never explains the distinction between artifact_path and artifact_relative_path, the effect of audit_record_limit (including the 0-100 range), or the optional nature of version_id. With 0% schema coverage, the description should compensate more than it does.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: export a deterministic replay package for one draft version. It enumerates what the package bundles (graph/provenance integrity, Registry support, optional saved artifact verification, recent MCP audit records). It does not explicitly name which sibling export tool (e.g., export_draft_review_artifact) it differs from, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No statement of when to use this tool versus the many sibling export/review tools (export_draft_review_artifact, review_draft_bundle, export_tool_call_audit_log_evidence). There are no prerequisites or exclusions given. Usage must be inferred entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.