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

Goes well beyond the readOnly/idempotent annotations: declares the rate class (600 requests/hour), explains that non-computable cases return an 'error' field, and discloses the n-counting rule (responses missing either value are excluded). It also spells out the returned statistical set, so the agent knows exactly what evidence comes back.

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?

Front-loads what the tool is, then layers code formats, analyzable question types, and return shape in a logical order with no filler sentences. It is a dense single block, though — the return-value enumeration is long and partly duplicated by the output schema.

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?

Covers everything an agent needs to call it correctly: valid question types, code addressing syntax, pair-completeness semantics, rate limit, and error signaling. Since an output schema exists, the return-value prose is surplus but harmless rather than a gap.

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 a baseline of 3 would apply, but the description adds real meaning: how variables are addressed (Q1 whole question, Q3.1 matrix row, Q2.3 checkbox entering as 0/1) and that options enter by numeric export code. It also reinforces the exactly-two constraint on the questions array beyond the schema's terse wording.

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 and precise statistical procedure: 'Computes a PAIRED-samples t-test between exactly two survey variables answered by the same respondents,' with a concrete example (before/after item pair). This clearly separates it from siblings like run_correlation and run_regression, which an agent could otherwise confuse with it.

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 condition for use (paired samples, same respondents) and an explicit alternative for a different need — 'the same and other statistics ... can be computed from the raw responses returned by list_survey_responses.' It also states a hard exclusion ('free-text cannot be analyzed'). It does not explicitly say when to prefer run_correlation or run_regression over this tool, so it falls short of a full when/when-not/alternatives treatment.

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