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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the free-tier rate limit (3 per IP per day for new registrations without a key), the consent requirement (accept_terms: true), the api_key recommendation, and the in-call wait ceiling — all behavior an agent cannot infer from structured fields. It also flags the synthetic-persona disclaimer, which prevents the agent from presenting results as real public opinion.

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?

Dense but front-loaded: the capability, the disclaimer, the call mechanics, and the return contract come in that order, and each sentence carries operational information. The two disclaimer sentences ('response simulation by synthetic personas' / 'not a survey of real people') overlap slightly and could be merged without losing meaning.

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?

For a 9-parameter, open-world, non-read-only tool with no output schema, the description covers the important gaps: return status values, consent, rate limits, and wait semantics. The one omission is the shape of survey_result, which — with no output schema present — the description could only name but not explain, leaving the agent to discover the response payload at runtime.

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%, so parameters are already well documented; the description only restates the persona range (10-100), the 3-question cap, and the 30s wait, which duplicate schema text. It adds a small amount of framing around accept_terms, but nothing about target_description, idempotency_key, or api_key usage that the schema does not already say.

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?

The description opens with a specific verb and resource: 'Run a free response simulation across 10-100 synthetic Japanese personas (up to 3 questions)', which is far more concrete than the tool name alone. It also distinguishes itself from the polling sibling implicitly by stating it returns 'running' with next_tool, but it never names cloneai_get_survey_result or the Agent Hub siblings, leaving the routing inference to the agent.

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?

Clear context for use: one call submits and waits up to 30s, and wait_for_completion=false returns a job handle immediately, which tells the agent when to prefer the async path. What is missing is an explicit when-not statement or a named alternative (e.g. 'if status is running, call cloneai_get_survey_result'), so the follow-up step is only hinted at via 'next_tool'.

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