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

No annotations are provided, so the description must fully convey behavioral traits. It only states the tool classifies content, but does not disclose whether it is read-only, what side effects exist, or any constraints like rate limits or auth requirements.

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 very short (one sentence) and front-loaded with the tool's core purpose. However, it sacrifices completeness for brevity, using a bullet-like format that is somewhat unclear (e.g., 'flagged?' is a question).

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 no output schema, the description should explain return values in more detail. While it lists fields, it does not specify their types, examples, or any error conditions. The single parameter is also under-described, leaving the agent uncertain about input requirements.

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?

The input schema has 0% description coverage for its single parameter 'text'. The description does not add any semantic meaning beyond the schema's type 'string', failing to clarify what input is expected (e.g., acceptable length, language, encoding).

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 clearly indicates the tool performs content-safety classification, listing output fields (flagged?, categories, severity, reason). It distinguishes from sibling tools like edit_clip, extract, etc., which are not related to moderation.

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?

No guidance on when to use this tool vs alternatives such as search or summarize. There is no mention of prerequisites or context that would help an agent decide to call moderate instead of another tool.

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