Content moderation

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

Beyond annotations (readOnlyHint=false, openWorldHint=true, etc.), the description adds that the call costs credits from the account wallet and discloses the output includes categories and excerpts. This provides useful behavioral context not present in annotations, though it does not detail side effects or error handling.

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, well-structured sentence that front-loads the core purpose and includes the cost implication at the end. No unnecessary words or repetition; it earns every word.

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 complexity (4 params, nested object, no output schema), the description is incomplete. It mentions the decision output and categories/excerpts but does not specify required inputs, behavior when both text and image are provided, or error handling. The cost note is useful but the overall context is not fully specified.

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 only 25% (only 'policy' has a description). The description says 'Text or an image' but does not clarify the relationship between text, image, and imageUrl, nor whether any are required. It fails to compensate for the lack of parameter documentation in the schema, leaving significant ambiguity.

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 ('moderate') and resource ('text or an image') against a policy, with a clear output (allow/review/block) and supplementary data (categories and excerpts). It clearly distinguishes itself from siblings like parserail_classify by emphasizing policy-based decisions rather than generic classification.

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 implies usage when content needs policy-based moderation, but it does not explicitly state when to use it versus alternatives like parserail_classify or parserail_sentiment. No when-not-to-use guidance is provided, though the purpose is clear enough for an agent to infer the primary use case.

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