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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description adds context annotations cannot: a PREMIUM license gate, and that invalid input never raises a protocol error — it returns {"error": ...} so retry after correction is safe. It also discloses that supplying a fingerprint changes the output (adds person-specific numeric targets), which is real behavioral information.

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 one-sentence purpose, then scope, then workflow, then errors — a sensible order. It loses a point because the 'typical input/returns' JSON sketch partly restates a return shape the output schema already carries, and the license note is wedged mid-paragraph rather than flagged up front.

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 two-parameter, nested-object tool with an output schema, this covers everything an agent needs: precondition, what it returns conceptually, what it does not do, the retry/error contract, and the next step in the pipeline. Nothing material is left to inference.

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 coverage is 100% and the fingerprint parameter is already documented as a voice_fingerprint output, so the baseline would be 3. The description goes further by explaining the consequence of passing it — 'when a voice_fingerprint result is supplied, adds numeric targets to hit that person's voice' — which the schema does not state. Marginal but genuine added meaning.

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 artifact — 'produce a precise rewrite brief that de-AIs a draft, with numeric targets' — and immediately disambiguates with 'returns a brief, not rewritten prose.' It also separates itself from verify_rewrite by name, so an agent can pick it out of a sibling set that includes ai_tell_scan and voice_fingerprint without opening any schema.

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?

'Use after a scan has identified what to fix' gives the precondition, and 'Not for checking whether a rewrite worked (verify_rewrite)' gives an explicit exclusion with the alternative named. The follow-on workflow ('Apply the brief with your agent, then confirm with verify_rewrite') tells the agent where this sits in the sequence.

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