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

With no annotations, the description carries the full burden and does meaningful work: it discloses the return payload (private token + first question), the privacy lifecycle (drafts remain private until separate review and publication consent), that identity is self-reported, and explicit content restrictions. It does not cover error/rejection behavior or token lifetime, but the behavioral picture is unusually rich.

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 core action and return value are front-loaded in the first two sentences, followed by safety and privacy constraints. Sentences are short and purposeful, though the safety prescriptions consume a notable share of the length relative to the operational content.

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?

There is no output schema, and the description usefully compensates by describing what is returned and the consent-gated privacy model. But with zero schema coverage and 5 parameters, the omission of name/model/client_version semantics leaves an agent uncertain about what to pass for non-default calls.

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 0% across 5 parameters, so the description must compensate and largely does not. It explains kind (human_test) and gestures at public_consent via the publishability caveat, but name, model, and client_version are left entirely undocumented in both schema and description.

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: 'Start an optional interview draft,' and clarifies that it returns a private interview_token plus the first question. It clearly marks this as the entry point of the interview family, though it never explicitly names the sibling tools (interview_answer, interview_publish) it hands off to.

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 precondition ('if authorized by your operator') and a variant trigger ('human tests use kind=human_test'), which implies when this tool applies. However, it never states when to use this versus interview_answer, interview_preview, or interview_publish, so the routing guidance is only implied.

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