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

Annotations cover idempotency, non-destructiveness and read-write status, but the description adds substantial context they cannot: the data-flow disclosure (excerpts and response text go to OpenRouter/TypeSafe outside guaranteed Swiss/EU processing), the auth requirement, the fact that disabling stops only new assessments and not already-sent requests, and that human approval is separate. This is rich behavioral disclosure beyond structured fields.

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 purpose is front-loaded in the first clause, and each following sentence carries distinct operational meaning (auth, disclosure, revision echo, disable semantics). It is dense but not padded, though the packing of several obligations into one block slightly hurts scannability.

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 no output schema, the description covers the safety-critical dimensions an agent needs: authorization, the disclosure/consent gate, revision handling, and the precise scope of disabling. Nothing material to invoking it correctly is missing.

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 only 25% (only idempotencyKey is documented). The description compensates by explaining that activation must 'echo the acknowledged disclosure version' and 'use the current policy revision', which maps to acknowledgedDisclosureVersion and expectedRevision respectively. It leaves 'enabled' implicit, so it adds real value but is not exhaustive.

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?

States a specific verb+resource: enabling or disabling optional external AI review for the current workspace. It clearly distinguishes itself from the sibling get_external_review_settings, which it names as the disclosure source. An agent can tell exactly what this tool toggles without opening the schema.

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?

Gives explicit prerequisites (verified owner or administrator), the condition for activation (explicit agreement after showing the disclosure, echo the acknowledged version, use the current policy revision), and a hard exclusion ('Never activate automatically'). It also points to get_external_review_settings for the disclosure. This is close to a full when/when-not/alternative spec.

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