build_recommendation_test

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that no assistant is queried, that rankings are not public and vary by wording/location/session, and that the tool only produces prompts and a rubric. It stops short of describing the artifact's shape (how many prompts, format), which matters given there is no output schema.

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 deliverable and the key negative constraint, and the handoff instructions are actionable. It is slightly padded by editorializing about tools claiming a definitive 'AI ranking', which is defensible framing but not strictly load-bearing.

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 no annotations and no output schema, the description does cover purpose, limits, the returned artifact type and next-step handoff. It is nearly complete, missing only concrete detail about the generated prompt set's format and size.

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 brand, market and category are already documented, and the description adds only a general note that answers vary by location — which reinforces the market parameter but gives no new syntax or constraint. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (Generate) and resource (the prompt set plus scoring rubric) with an explicit scope boundary: 'This tool does NOT query any assistant.' That negative statement cleanly distinguishes it from the sibling check_ai_visibility without naming it directly. An agent can tell what artifact it produces.

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?

Explicit conditional routing: if the calling assistant can search the web, run the prompts and report back; otherwise hand them to the user to run monthly. It also states what the tool cannot do, which prevents misuse as a ranking oracle. Nothing about when to reach for it is left to inference.

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