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

Annotations declare a non-read-only, non-idempotent, non-destructive, closed-world write, and the description adds real behavioral limits (what it cannot revoke/clear, that it must not be inferred) plus a pointer to a workflow guide resource. It stops short of describing idempotency behavior or what the recorded state affects.

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?

Four dense sentences, front-loaded with the action and the confirmation prerequisite, and every sentence carries a distinct constraint or parameter mapping. The telegraphic field list is compact rather than padded.

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 mutation tool with a nested free-form payload and no output schema, the description supplies the field vocabulary, the precondition, the forbidden inference sources, and the non-capabilities. The one remaining gap is any indication of what the recorded permission enables or returns.

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 67% and the payload is an opaque additionalProperties:{} object, so the schema gives the agent essentially nothing about the actual business fields. The description enumerates email, sourcePath (with a concrete path template), evidence, and evidenceAtMs, which is the only place those semantics exist.

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?

Names a specific verb and resource (record permission evidence for an already-imported contact), and the 'after human confirmation' qualifier narrows the scope. It is clear what the tool does, though it does not name a sibling tool it competes with despite the large email/contact tool family.

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?

Explicit preconditions ('after human confirmation') plus hard exclusions ('Never infer permission from a purchase, RSVP or membership') and explicit non-capabilities ('Cannot clear a revoked grant, unsubscribe, bounce or complaint'). This tells the agent both when to call it and when calling it would be wrong.

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