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

Annotations cover the write/read profile, and the description adds genuinely non-obvious behavior: it returns a first clarifying question or a 'plan is ready' status, and out-of-scope questions silently create no study. It does not explain idempotency or what happens on repeat calls, so it stays short of a 5.

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?

Four short sentences, front-loaded with the purpose and trigger, then input handling, then return behavior, then the edge case. No filler and every sentence carries distinct information.

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, the description does the work of describing return values (clarifying question vs. plan ready) and the no-op edge case. It leaves the natural next step (answer_clarification / confirm_plan) unstated, which is a minor gap given the sibling set.

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 single parameter's format and length bounds are already documented. The description's 'pass the user's question in their own words; don't rephrase or improve it' adds an emphasis on verbatim fidelity, but largely restates what the schema already says.

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 ('Start customer research with real human participants') and implicitly distinguishes itself from the sibling analyze_now by contrasting human participants with 'synthetic model feedback'. An agent can identify what this tool produces without opening 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?

Gives a clear triggering condition ('when a product decision needs evidence rather than synthetic model feedback') and a constraint on input handling, but never names the alternative tool (e.g., analyze_now) or states explicit exclusions beyond out-of-scope questions creating no study.

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