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

Annotations already mark destructiveHint=true and readOnlyHint=false, but the description adds useful behavioral context: the new secret is returned exactly once and the old secret remains valid during a grace window. This tells the agent that the secret is only visible at rotation time and that invalidation is deferred, which is valuable beyond the annotations. No contradictions with the structured hints.

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?

A single sentence, no filler. It front-loads the action ('Rotate the signing secret') and packs the essential behavioral details (return-once, grace period) into one concise clause. Every word earns its place.

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 2-parameter, destructive, no-output-schema tool, the description covers the most critical behavior: the secret's one-time return and the grace period, which directly affect how the returned value must be handled. What is missing is any detail about how the parameters map to the target webhook and what the response format is, but the core operational behavior is well captured.

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 only 50%: 'id' has a description ('Job id or alias'), but 'webhook_id' is bare. The tool description does not mention either parameter or clarify what 'webhook_id' identifies (beyond the name webhook). It does not compensate for the missing schema description, leaving webhook_id's role and format ambiguous.

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 action (rotate the signing secret) and a key side effect (new one returned once, old stays valid for a grace period). While it doesn't explicitly say 'job' in the description, the tool name and annotation title ('Rotate job webhook signing secret') make the resource specific and distinguish it from the sibling 'hires_rotate_webhook_secret'.

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?

The description provides no guidance on when to rotate the secret (e.g., after suspected compromise) and does not mention any alternatives or prerequisites. It also does not explicitly reference the sibling tool 'hires_rotate_webhook_secret' to clarify the distinction between job-specific and generic webhook secret rotation. The only behavioral note is about the grace period, which is more behavioral than usage guidance.

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