rotate_callback_secret

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

Annotations already declare destructiveHint=true; the description adds substantial behavior on top: the secret is returned exactly once and must be stored immediately, already-queued deliveries retain the secret they were signed with, and the call performs a side effect by migrating a settings-webhook-URL account to webhook endpoints. These are exactly the operational facts an agent needs before invoking a destructive rotation.

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 one-time return warning is front-loaded right after the purpose, which is the correct ordering, and the side-effect note follows. The ACCESS block is essential rather than filler. A small amount of compression is possible but nothing is genuinely wasteful.

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 single-parameter mutation with an output schema, the description covers auth prerequisites, the one-time secret return, and the queue/migration side effects. It stops short of saying whether the old secret remains valid for newly generated deliveries or whether any propagation delay applies, which would matter in a rotation workflow.

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 100% with a single required profile_id, so the schema already carries the definition (24 hex characters). The description adds only the framing of that ID as a sub-account, matching but not extending the schema, so the baseline 3 is appropriate.

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 names a specific verb and resource ('Rotate a sub-account's callback signing secret') and defines precisely which secret is meant (one used to sign every callback_url delivery). It implicitly separates itself from the sibling rotate_webhook_endpoint_secret by scoping to the sub-account, but never names that sibling, so an agent must infer the distinction.

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 usage context is clear: rotate when you need a new signing secret, and an account still using the settings webhook URL is migrated to webhook endpoints first. It also states the access prerequisite (Proof account, PROOF_API_KEY, restart the server) and explicitly rules out start_login as a path. The only gap is that it does not explicitly route per-endpoint rotation to rotate_webhook_endpoint_secret.

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