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

The description directly contradicts the openWorldHint=true annotation by stating 'no external research or outbound actions.' This is a clear inconsistency that misleads the agent about the tool's ability to access external data. Although it adds useful details about payment and non-rewriting, the contradiction warrants a score of 1.

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?

The description is a single paragraph but logically organized: purpose, categories, output, constraints, payment. It is not excessively verbose and front-loads the core action. Minor redundancy (e.g., 'Returns a draft for human review' could be implied) but overall efficient.

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?

Given the tool has a nested object, 5 parameters, and no output schema, the description should explain how to construct the input. It does not cover any parameter semantics, and while it describes the output format, the absence of input guidance makes the tool hard to invoke correctly. The payment requirement is mentioned but not tied to specific fields (e.g., payment_signature).

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 0% schema description coverage, the description must compensate by explaining parameters. It does not mention any of the 5 parameters (input, result_expires, idempotency_key, result_signature, payment_signature) or their meanings. The nested input object fields (brief, audience, source_text) are also undocumented, leaving the agent to guess.

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 action (review marketing/social copy for policy-risk language) with concrete categories (health claims, financial guarantees, discriminatory language). It clearly distinguishes itself from generation tools like ad_copy or social_posts by emphasizing review and non-rewriting. The output format is also explicit (verdict, flagged spans, reasons).

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 description gives clear context: use this when you have marketing or social copy to vet for policy compliance. It also includes a notable exclusion ('Do not rewrite the copy unless asked'). However, it does not explicitly name alternatives or when NOT to use it, leaving some 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.