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

Annotations already declare non-readOnly, idempotent, non-destructive, closed-world, so the mutation profile is known. The description adds genuinely new behavior: it returns remaining open questions (making it a progress probe, not just a writer) and reports ready_for_protected_draft only for eligible ordinary documents, with no charge before payment. Missing only what happens on invalid keys or partial saves.

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?

Two sentences, front-loaded with the write action before the return-value and pricing nuance. The second sentence is clause-heavy (open questions + eligibility + $0 + payment ordering) but every clause carries information an agent needs.

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, so the description carries the return-value burden and does so at a high level: open questions plus a ready_for_protected_draft boolean. For a 3-param, nested-answers write tool that is close to sufficient; only the shape of the returned open-questions collection and error behavior remain unstated.

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 the answers property already documents 'Question key => the person's answer' and the one-choice rule, so the description's parenthetical restates rather than extends it. case_id and access_token provenance from start_document is likewise already in the schema. 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 action and resource: saves the person's answers, keyed by question key, scoped to a case. An agent can tell this is the answer-submission step of a document workflow, though it never names a sibling it is not (e.g. prepare_protected_draft) and uses 'case' where the title says 'document', leaving a small naming seam.

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 second sentence implies the loop (submit answers, receive still-open questions, repeat until ready_for_protected_draft appears) and mentions a $0 pre-payment draft gate, which nudges the agent toward when to call it. But there is no explicit when-not or alternative — nothing says what to do instead when questions remain unanswered or when the case is already paid.

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