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

Annotations cover the state profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower, and the description still adds real context: the security consequence (the phone opens their front door) and a per-setup attempt limit. Nothing here contradicts the annotations; only the success/failure response shape is left unstated.

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?

Three short sentences, front-loaded with the action and immediately followed by the reason it matters and the flow pointer. The 'front door' clause is flavor but it does convey stakes efficiently; nothing is wasted.

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 three-required-param, no-output-schema verification step, the description supplies what an agent needs: which code, the retry ceiling, and the next tool. Only the success/failure outcome (what a bad code returns, whether it consumes a try) is unspecified.

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 100%, and each of the three parameters (code, setup_id, status_token) is documented in the schema itself. The description adds no syntax, format, or secret-handling detail beyond what is already there, 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?

Specific verb ('Checks the code') plus the concrete resource (the code the person read back), and it frames the outcome — proving phone ownership. It does not name the adjacent sibling send_phone_code or partner_confirm_code, so an agent must infer the ordering from the 'Next: start_checkout' pointer.

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?

Clearly places the call in the flow: the code must already have been read to the person, and the stated next step is start_checkout. It also gives the retry budget ('Five tries per setup'), which is genuine operational guidance. It stops short of naming alternatives such as partner_confirm_code or saying when not to call.

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