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

The description adds substantial behavior beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false): it spends AI-tester runs, creates a new project, and requires the latest proposalId with the concrete failure mode PROPOSAL_NOT_FOUND when stale. It also discloses the return shape (testId, final personas/plan, startedMessage with expected duration) and that results are retrieved via wait_for_results.

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-loaded with the action and approval prerequisite, then prerequisites, failure mode, edits, return values, and the sibling alternative in a dense, well-ordered sequence. Every sentence carries distinct information with no filler.

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 launch/mutation tool with a rich nested edits schema, the description covers the full calling lifecycle: prerequisite tool, approval requirement, id freshness and failure mode, return values, results retrieval, and the correct alternative for re-runs. An output schema exists, yet the description still appropriately orients the agent on what comes back.

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 0%, so the description must carry parameter meaning, and it does explain proposalId semantics (latest id only, revise replaces earlier ids, stale id fails) plus the edits intent (add/remove tasks or questions, swap personas). It leaves the audience sub-object and addLearningGoals variants undetailed, so it doesn't fully compensate for the 0% coverage, but the high-value semantics are present.

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?

Starts with a specific verb and resource ('Starts the AI usability test for a proposal') and immediately roots the tool in its lifecycle by naming the producing siblings propose_usability_test and revise_usability_test. It also distinguishes itself from relaunch_usability_test for a different scenario, so an agent can disambiguate without opening schemas.

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?

Explicitly states the when ('only after the user has reviewed the plan and explicitly approved') and the when-not rationale (spends AI-tester runs, creates a new project). It names the alternative relaunch_usability_test and the exact condition that selects it (running another batch on an existing project to avoid a duplicate).

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