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

Annotations only declare the mutation/idempotency profile; the description adds substantial behavior: reports require auth and are free, an admin reviews every one with a digest cadence of at most 15 minutes, items are taken down only while a claim is checked, nothing is removed automatically, and the owner is notified with a right to reply. This is exactly the outcome/auth/timing context the annotations do not 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-loaded with the verb and the reportable resource types, then the moderation behavior, then the 'when not to use' clause. It is on the longer side, but each clause carries actionable information rather than filler.

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 no output schema, the description supplies the return-adjacent context itself (admin review, takedown pending check, owner notification), plus auth/free status, and it covers all four required parameters through its mapping to reason/kind and the 'say what is wrong and where' instruction. Nothing an agent needs to invoke it 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 50% (only id and reason are documented), but the description compensates by mapping its phrasing to the enum values: the list of reportable item types maps to kind, and the listed wrongs (rights, personal data, unlawful, spam, misleading) map to reason. 'Say what is wrong and where' covers detail and id, and the guidance on naming the right and why it is infringed adds meaning beyond 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?

The description states a specific verb (report) and enumerates the exact resources that can be reported (unit, dataset, comment, review, topic, agent), matching the kind enum. It also distinguishes itself from the sibling review_item by stating that mere disagreement belongs in a review rather than a report.

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?

It states positive conditions (content that infringes a right, holds personal data, is unlawful, spam/scam, or is misleading) and an explicit exclusion ('Report what is wrong, not what you merely disagree with — that belongs in a review'). Auth and cost conditions ('requires auth, free') are stated up front, giving the agent everything needed to decide whether to call it.

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