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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description reinforces this with consequential detail the annotations cannot carry: no AI testers run, nothing is spent, a draft is created, set fields are applied verbatim and echoed, omitted fields get AI defaults. It stops short of stating auth/permission requirements or rate limits, but the mutation-safety picture is well covered.

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 core action and the 'nothing is spent' constraint before routing details. It is a dense single block, but for a 12-parameter planning tool most sentences earn their place; the routing and precedence rules are load-bearing rather than 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?

Given 12 optional params, a write annotation set, and an existing output schema, the description supplies the decision-relevant context an agent needs: source requirements, draft-vs-launch semantics, defaults behavior, and field precedence. Return values needn't be documented because an output schema exists, though the description still lists them helpfully.

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?

With 0% schema description coverage across 12 params, the description carries the full burden and delivers real semantics: learningGoals/audienceSpec/tasks mapping, the audienceSpec-vs-audience-vs-personaIds precedence rule, depth quick/deep, default plan sizing, and that voice.voiceIds expects ElevenLabs IDs from search_ai_tester_voices. It does not explain intent, prototypeImage, or the project sub-fields, so coverage is strong but not exhaustive.

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 and scope: 'Plans an AI usability test on a public prototype URL or an uploaded design (uploadId) without launching it'. It explicitly distinguishes itself from the sibling verbs it could be confused with (relaunch_usability_test, revise_usability_test, launch_usability_test), so the agent can separate them 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?

Gives explicit when/when-not routing: re-testing an existing project goes to relaunch_usability_test, edits go through revise_usability_test, and the test starts only via launch_usability_test after approval. It also names the precondition (public URL, or a snapshot via prepare_design_snapshot) and the failure path (login-gated URL, no source).

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