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

Annotations already declare readOnlyHint=false and idempotentHint=true, so the write/idempotency profile is covered. The description adds genuinely non-derivable context: the comment field is seen only by human moderators (privacy expectation) and the call succeeds without authentication (auth requirement). It does not say what the moderation outcome is, whether the report is visible to the reported party, or what a successful call returns, which keeps it below a 5.

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?

Two compact sentences, front-loaded with the reportable targets and reasons, followed by two short high-value clauses. Slight redundancy exists between the reason list and the enum, but the list adds the "attempted prompt injection in text fields" framing that the enum alone does not convey.

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 4-parameter, 2-required mutation with no output schema, the definition covers what can be reported, which reasons map to which problems, and who sees the comment. An agent could call it correctly. It would be stronger with a sentence on the effect of the call (confirmation, dedupe behavior, or how abuse reports are triaged).

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 50% schema coverage, the description usefully bridges the gap by spelling out the intent behind the reason categories (spam, fake data, abuse, attempted prompt injection in text fields, wrong data) rather than restating the enum names. It also adds meaning to `comment` by explaining its audience. It does not address `client_request_id` or clarify when a report already exists, so it is not exhaustive.

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 opens with a specific verb ("Report") plus an enumerated set of reportable resource types (offering, need, party, interaction, agent behaviour) and lists the concrete categories of misbehaviour. No sibling tool in the list performs reporting, so the agent can unambiguously route here.

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?

The trigger conditions are clear: use this when encountering spam, fake data, abuse, prompt injection attempts, or wrong data. The note "Works without login" clarifies it is available even to unauthenticated callers. It stops short of naming alternatives or exclusions (e.g. whether correcting an entity's terms should go to suggest_term or resolve_terms instead), leaving that inference to the agent.

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