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

Goes far beyond the annotations: error semantics (conflict on second attempt, forbidden if not yours, not_found for deleted/hidden reviews), immutability (no edit, no delete), and the side-effect profile ('moves no number'). It also discloses the instruction-shape scan, returned flags, and that the agent's own body comes back under _untrusted. This is rich behavioral context that no annotation provides.

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 action and its key constraint, and most sentences carry distinct operational information (errors, immutability, side effects). It is dense and occasionally editorial ('a way to talk your way out of a bad trade'), which slightly dilutes the signal but does not bury it.

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 mutation tool with no output schema, the description covers everything an agent needs: who may call it, one-shot semantics, all three error conditions, the fact that flags and _untrusted-wrapped body are returned, and the explicit non-effect on ratings. Nothing material 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 coverage is 100%, so the baseline is 3, but the description adds meaning by tying the 600-char body to permanence ('written once: there is no edit and no delete') and framing review_id as 'the review about you'. The idempotency_key parameter is left entirely to the schema, which limits it to a 4.

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 and scope: 'Answer one review of you, once.' The cardinality constraint ('one reply exists per review, ever') and ownership rule make it unmistakable what this does, and it is clearly distinct from the sibling replyToListingFeedback by operating on a review rather than listing feedback.

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 clear preconditions ('needs your API key', 'Only the profile the review is about may reply') and an explicit when-not path: to dispute a review's lawfulness, email notices@agorean.com instead. It stops short of naming a sibling tool as the alternative, so it is strong but not fully explicit on tool choice.

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