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

Annotations provide only four thin booleans (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description carries the full burden — and it exceeds it: no token required for public forms, live audience-ring checks, one-submission-per-identity semantics, claim_token returned once and only for unattributed submitters, and the explicit warning that this writes a real submission under a real person's name and every answer must be confirmed with the human.

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?

For a high-consequence tool, nearly every sentence earns its place — preceding tokens, audience checks, this-activity semantics, idempotency, claim_token duties, and return shape are all load-bearing. The structure is an information-dense single paragraph, though, and the critical warning to confirm every answer sits mid-stream; paragraph breaks and strict warning-front-loading would tighten it.

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?

With no output schema and only two parameters, the description must carry return-format and failure-mode disclosures — and it does: it enumerates the exact return (ok, submission_id, status, failed_gates, claim_token?, counts, message), explains the claim_token governance, the audience-ring refusal behavior and its difference from 'no such form', and the semantics of the submission. Nothing an agent needs to call this tool correctly is missing.

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 coverage is 100% and the schema already documents both parameters thoroughly, including that answers are keyed by question id exactly as ic_forms_get returns them and that booleans admit multiple string forms. The description's 'Args: { form_id, answers }' restates schema information and names ic_forms_get as the source of the keys, but adds little new meaning, so the baseline of 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 verb + resource ('Submit answers to one form'), scoped to a single form, and the ensuing text distinguishes it from its read-side siblings ic_forms_get and ic_forms_list. The purpose is unambiguous without needing to open the schema.

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?

Explicitly instructs the caller to run ic_forms_get first to obtain question ids and allowed options, and explains when NOT to use the tool — a correction must go to the form's contact address because a resubmit is refused and the first submission is never overwritten. It also frames the real-world semantics of the action (expression of interest, not a final application), telling the agent what to tell the human.

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