audit_event_emit

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

No annotations exist, so description carries full burden. Discloses that the server assigns event_id/timestamp/prev_hash/hash, requires AUDIT_STREAM_URL environment variable, returns persisted event, and returns structured error if env var missing. Comprehensive for a POST operation.

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 sentences plus examples. Front-loaded with core action, then provides context and use cases. No redundant information. Efficient and well-structured.

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, description explains server-side field assignment and return value. Also mentions error condition. Complete for a simple post tool with well-documented parameters.

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 covers all parameters (100% coverage), so baseline is 3. Description adds value: explains convention for 'kind' (snake_case, matching producer kinds, 'other' for ad-hoc) and 'source' as stable producer identifier. Goes beyond schema descriptions.

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 states the verb (POST), resource (one governance event to audit-stream-py), and scope. It distinguishes from sibling tools like audit_event_compose and audit_events_query by focusing on emitting a single event via the audit-stream-py instance.

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?

Explicitly states when to use ('record a governance moment from inside a chat') and provides examples (e.g., manual override, human-approved exception). Does not explicitly exclude other scenarios, but context is clear.

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