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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds genuinely new behavior — the opt-in gating and the refusal path — plus a trust classification ('untrusted respondent content'). That is meaningful context beyond the structured fields.

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 what the tool returns, then prerequisites, then the trust caveat. No filler and nothing buried.

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?

An output schema exists, so return shape need not be explained; the description covers what it returns, the gating requirement, and the data-trust caveat. Ordering/pagination behavior is unstated, which is a minor gap for a listing tool.

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?

Only one parameter (form) and schema description coverage is 100%, so the schema already documents it fully; the description adds no format or resolution detail for the id, slug, or push handle. Baseline 3 is appropriate.

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 resource and viewpoint: 'Who is mid-fill on a form and what they have typed so far,' which clearly separates this from submitted-response tools like fillo_list_responses. It does not name a sibling explicitly, so differentiation is implied rather than asserted.

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 concrete precondition for use: the form must have saveProgress and draftAnswersVisible opted in, otherwise a clear refusal. It does not name an alternative tool for the case where a caller actually wants submitted data, so routing guidance is partial.

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