list_safety_assessments

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

No annotations provided, so description fully bears the burden. Discloses source types, behavior with/without callId, case of missing API key, precondition, and empty array semantics. Clearly read-only.

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?

Relatively verbose but each sentence adds unique information. Front-loaded with core action. Could be slightly trimmed but effective.

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?

No output schema, so description should explain return structure. Mentions ordering and empty array meaning, but does not describe fields of each assessment (e.g., content, severity). Gap in completeness.

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 coverage is 100%, but description adds meaning: ordering when no callId (flagged first then most recent), clarifies callId targets llm_calls.id, and provides context like default/max already in schema. Adds value beyond 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?

Description clearly states it lists safety classifier assessments (OpenAI Moderation), specifies filtering by callId or account-wide, and distinguishes from sibling tool classify_calls_batch.

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?

Explains when to use with/without callId, precondition that safety classification is disabled by default, meaning of empty array, and use case for AI agents. Does not explicitly list when not to use, but contrasts with classify_calls_batch.

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