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

Annotations flag destructiveHint/openWorldHint but not the specifics; the description supplies them: previous links and codes are invalidated (i.e., what actually gets destroyed), a rate limit of a few per hour with the rate_limited signal, and the required auth scope. That is real behavioral context 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?

Four tight sentences, front-loaded with the action, then consequences, then limits, then guidance. Every sentence carries unique operational information with no padding.

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?

Covers action, side effects, rate limit, prerequisites and routing to verify_email, which is more than enough for a no-argument action tool. The only omission is what the response looks like (no output schema exists), a minor gap.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a no-parameter tool applies. No wasted effort restating nonexistent inputs.

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 (send a new confirmation email to the owner) plus the payload (link and code). It is clearly distinguishable from the sibling verify_email, which is the validation counterpart rather than the re-issuing one.

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 an explicit trigger ('use only when the user hasn't received a code or verify_email says codes are locked') and implicitly excludes routine verification by naming the condition. It also states the required scope (locations:read, any member), which is a genuine prerequisite for calling it.

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