audit_event_emit

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

With annotations already covering the safety profile, the description adds substantial non-obvious behavior: the bearer token authenticates the MCP process rather than the claimed producer/tenant, the server assigns event_id/timestamp/prev_hash/hash, and the returned receipt does not prove durable storage or completeness. These are exactly the caveats an agent needs before emitting a governance event.

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 core action and endpoint are front-loaded in the first sentence, and each following sentence carries a distinct caveat (auth scope, approval/privacy, server-assigned fields, receipt limits). It is dense but earns its length; only the closing receipt caveat could be trimmed without much loss.

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?

For a non-idempotent, open-world mutation with no output schema and a nested payload object, the description covers the essential ground: where it POSTs, what is sent, what auth means, safety/privacy constraints, server-assigned fields, and the return shape. An agent has enough to call it correctly.

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 100%, so kind, source, and payload are already fully documented in the schema, including the caller-asserted source warning and the 'other' kind fallback. The description only restates 'kind, caller-asserted source, and payload' without adding format or validation detail beyond the schema, so the baseline 3 applies.

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 precise verb+resource: 'POSTs a governance event to the audit-stream-py instance configured by AUDIT_STREAM_URL and AUDIT_STREAM_TOKEN.' That clearly separates it from read-side siblings like audit_events_query or audit_event_inspect. However, it never names the closest alternative, audit_event_compose, so sibling selection still requires inference.

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?

It gives concrete preconditions: obtain user approval before recording, and omit secrets/personal data unless the service is approved for them. This is clear operational context, but it stops short of an explicit when-to-use-this-vs-a-sibling statement (e.g., compose vs emit, or when the token is not configured).

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