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

Annotations already mark this read-only, idempotent, and non-destructive; the description adds substantial behavioral context: bearer-credential privacy, bounded polling, terminal states, the contents of resolved results, and caveats that proof records process rather than guaranteed truth and that task/rationale is untrusted data. This goes well beyond what annotations convey.

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 dense but well-organized: purpose and the security constraint come first, followed by polling, terminal states, and result caveats. Every sentence adds operational or safety value, and none merely repeats the schema or annotations.

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?

Even with no output schema, the description tells the agent what terminal states to expect, what resolved results contain, how to manage polling, and how to treat the returned data. Combined with the annotations and the clear source of status_url, this is sufficient for correct invocation and interpretation.

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 description enriches status_url meaningfully by calling it a bearer credential, saying it must be kept private, and tying it to me_human_verify, going beyond the schema's 'Private URL from purchase acceptance.' However, wait_seconds is not clearly explained in the description; 'briefly wait' and the polling guidance do not directly map to the parameter, so one of the two parameters remains under-specified.

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 action ('Retrieve or briefly wait') on a concrete resource ('existing Human Verify result') and explicitly distinguishes this from repurchasing ('without another payment'). It references the private status_url from me_human_verify, so an agent can tell this is the follow-up retrieval/polling tool rather than the purchase/verify sibling.

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 a hard prerequisite: use only the private status_url returned by me_human_verify, and warns that it is a bearer credential. It also provides explicit polling behavior (at most once every five seconds) and says to call again after retry_after_seconds, which makes the calling pattern unambiguous.

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