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

Annotations already cover read-only, idempotent, open-world, non-destructive traits, so the description is not obligated to restate them. It adds meaningful context beyond them: private repos fail, github_pr is not an arbitrary URL fetch, it is not a merge/payout/money check, and it does not post comments.

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?

Front-loaded with the core purpose, then behavior, then limits, in short telegraphic sentences with no filler. The clipped fragment style is dense but every sentence carries information; it is not padded.

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?

No output schema exists, so the description must convey return shape, and it does name the closed label set and structuredContent.rationale contents (met/unmet/unaddressed). That is nearly sufficient for a complex 7-parameter tool, though the exact structuredContent fields for requirement scores are only partially specified.

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?

With 100% schema coverage the baseline is 3, but the description adds semantics the schema does not: github_pr is packed into the submission and private repos fail, the 'when' pin filters by passage-date prefix, and requirements scoring is conditional. Only 'caller_ref' echo behavior is left to the schema.

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 and resource ('Advisory spec-versus-submission check') plus the output contract: a closed judge label of met/not_met/ambiguous. This distinguishes it from siblings like verify_claim and analyze_pr. Jargon such as 'cite packs' is undefined, which slightly blunts first-read clarity.

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?

Gives real usage conditions: empty/off-topic cite packs yield ambiguous, requirements are scored only when packed cites bear on them, and github_pr must be public. However, it never explicitly says when to pick this over verify_claim or analyze_pr, so tool selection is left to inference.

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