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

Annotations already declare destructive=true and non-idempotent, but the description adds the details that matter: credits are debited during execution and the estimate is claimed against the daily budget at submission, the action cannot be undone, there is a 30-call/minute key-wide rate limit, and the idempotency_key retry semantics. It also discloses a behavioral failure mode (kind_mismatch) that annotations cannot express.

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 critical credit warning and the routing pointer to get_study/estimate_study are front-loaded, and the per-kind block is table-like and scannable. It is long, but for 23 parameters and 9 kinds nearly every line carries a non-redundant constraint; only minor trimming (e.g. the opening aside) would be possible.

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?

Despite an output schema existing, the description notes that run_id, study_id and web_url come back and that the result arrives via get_study, removing any ambiguity about async delivery. Combined with per-kind field requirements, budget/credit rules and polling cadence, an agent has everything needed to invoke this correctly.

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%, so the baseline is 3, but the description materially exceeds it: per-kind defaults (50, or url_feedback 30, focus_group 8, society 100), the rule that only one kind's material may be passed, the image sourcing preference order (image_files > request_upload/image_refs > image_urls), and the warning never to invent download_url or file_id. These are semantic constraints absent from the schema.

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 ('ask the audience' / submit a study) with explicit consequence framing, and clearly distinguishes itself from siblings by naming estimate_study and get_study as the alternatives. The credit-spend warning immediately separates it from estimate_study, so an agent can route without opening a 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?

Gives explicit when-to-use rules: call estimate_study first unless the study is small, ask the user before submitting anything with confirm_recommended=true, poll get_study every 5-10 seconds and no faster than once per 10 seconds. It also states when to use study_id (follow-up on the same respondents) and how to pick a kind by what respondents are shown.

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