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

Adds substantial behavior beyond the readOnlyHint:false annotation: the one-time email verification link, human-in-the-loop click, one-time display of the new token, immediate revocation of old tokens, and rate limiting ('a few requests per hour per email'). The description is consistent with the mutation annotation rather than contradicting it.

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?

Six sentences with no fluff, each earning its place: purpose, parameter semantics, out-of-band flow, revocation, exclusions, and rate limit. Front-loaded with the core operation before branching into alternatives and constraints.

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 1-parameter tool with no output schema, the description covers the end-to-end flow (email → verify link → token display once), revocation, rate limiting, and routing to alternatives. Minor gaps: the synchronous API response is not described and behavior for unregistered emails is unstated, but these are small against the thorough flow documentation.

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 0%, so the description must carry parameter meaning, and it does: 'Provide the email the account was registered with' clarifies that the email must be the original registration address, not an arbitrary identifier. It does not specify behavior for unregistered emails, but the single parameter's core semantics are fully explained.

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 and resource: 'Re-issue the API token for an existing account.' It explicitly disambiguates from siblings by asserting 'It does not create a new account' and by naming rotate_token as a separate path, so an agent can route correctly 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 when-to-use conditions: 'self-service recovery path when a token was lost, rotated, or is being rejected as "invalid or expired"'. It names both alternatives — create_account for brand-new accounts and rotate_token for holders of a valid token — so the exclusion logic is complete and actionable.

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