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

Goes well beyond the annotations by disclosing state-dependent timing (queued/preparing stops immediately, being answered stops at the next step), data retention ('Answers given are kept'), and the error behavior for already-answered or failed questions. That is exactly the mutation semantics an agent needs before committing a destructive cancel.

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 sentences, front-loaded with the action and identifiers, then timing, then data-retention and error behavior. No filler and no repetition beyond what clarity requires.

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 described. What the description must supply for a destructive, state-transitioning cancel — when it takes effect, what survives, what errors, and what scope is excluded — is all present.

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 each parameter already documents its role and how runId relates to studyId/questionId. The description restates that either/or structure compactly and front-loads it, but adds no format, precedence, or validation detail the schema lacks.

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 ('Stops') and a precisely scoped resource ('one standalone Study question'), plus the two keying modes. The closing clause 'Not for multi-question runs' actively separates it from sibling run tools like run_study_questions and start_study_run.

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 an explicit exclusion ('Not for multi-question runs') and points to where the identifiers come from (ask_study / ask_audience). It does not name the sibling an agent should use instead for multi-question runs, so the routing is implied rather than explicit.

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