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

Annotations already cover write, idempotent, and destructive hints. The description adds the explicit warning not to retrieve the confirmation code, and specifies that the email is verified. This provides useful behavioral context beyond what annotations state, without contradicting them.

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 description is two concise sentences, with the primary action front-loaded and the critical warning included efficiently. No filler or repetition.

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?

While the purpose is clear and the warning is stated, the description does not explain the expected workflow (e.g., that a confirmation code will be sent later, or the roles of apply/confirm). With no output schema and missing parameter details, an agent might not fully understand the sequence or side effects beyond sending the email.

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 50% (projectId and idempotencyKey have descriptions), while claimVersionId and revision lack schema descriptions. The tool description does not explain any parameter's purpose or add semantics beyond the schema, leaving half the parameters under-documented.

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 verb 'Send' and the resource: the business statement, evidence, owner, validity, and reuse scope, to the reviewer's verified email. It also says to present source evidence for review, making the tool's role distinct from siblings like apply or confirm, which handle later stages.

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 instruction 'Never retrieve the confirmation code from the mailbox' implies this tool is for initiating the request, and retrieving the code is a separate step (likely the confirm tool). However, it doesn't explicitly name alternatives or state when to use this vs. apply or confirm, so some inference is required.

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