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

Annotations only declare the mutation/idempotency profile; the description adds operationally important facts not present there — no API key or x402 payment required, does not count against search quotas — plus a PII/API-key prohibition. That is exactly the extra context annotations cannot carry.

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-loads the purpose, then the call-to-action, then parameter/submission constraints, in compact sentences. Every sentence carries distinct information (what, when, required content, prohibitions, auth/quota).

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?

With an output schema present, return values need no explanation, and the description still covers required content, category/severity vocabularies, auth requirements, quota behavior, and privacy limits. Nothing an agent needs to submit correctly is missing.

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 100%, so all three parameters and both enums are already documented in the schema; the description largely restates the enum values and the message guidance. Baseline 3 applies since the description adds little syntax or semantic detail beyond the structured fields.

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 ('Report') and concrete resource types (bug, missing capability, bad search result, confusing schema) aimed at the Recall Kitchen team. It is unmistakably distinct from every sibling tool, none of which are feedback channels.

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?

Explicitly tells the agent when to use it ('instead of silently working around a problem'), which is a strong usage cue for an agent that might otherwise retry or improvise. It does not enumerate when not to file feedback (e.g., trivial/noise), so it stops short of a 5.

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