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

Annotations only declare readOnly=false and destructive=false, so the description carries the real burden and delivers: the out-of-band delivery precondition, the specific error code on unsupported pairs, and the account/auth requirement. This is well beyond what the annotations provide.

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?

Front-loaded with the core action, then constraints, then alternative routing, then access. Dense but purposeful; the ACCESS paragraph is slightly verbose though it conveys distinct, needed information.

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-param mutation tool with no output schema, the description covers the accepted inputs, the failure mode, the authentication prerequisites, and where the same goal is achieved otherwise. Nothing an agent needs to invoke it correctly is missing.

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%, so both parameters (id, code) are already documented and the description adds no syntax or format detail for them. The type/channel discussion clarifies surrounding semantics but those are not parameters of this tool, so baseline 3 applies.

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 (submit) and resource (OTP/challenge code for a pending verification), then precisely narrows the accepted cases. It distinguishes itself from siblings by naming the exact situations it handles versus where completion happens elsewhere.

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?

Explicitly lists when it applies (type email, type domain with channel email) and when it does not, including the exact failure (400 unsupported_for_type), and routes the agent to trigger_verification plus the phone/social/telegram completion paths. Nothing is left to inference.

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