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

Beyond the readOnly/destructive annotations, it discloses cost semantics (1 credit per search, refunded if the search can't run) and explains the `coverage` signal as a confidence indicator with prescribed handling. It also states what each example contains, so the agent knows what 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-loaded with the core action and the output composition, then usage and cost. Slightly long because it enumerates return fields that the output schema already covers, but every sentence still carries signal.

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 purpose, cost, result shape, the coverage confidence signal, and downstream usage in one place; the output schema handles return structure, so nothing an agent needs to call it correctly is missing.

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 all four parameters are already documented; the description restates the `brief` contents (product, audience, goal, tone) but adds nothing on `limit`, `platform`, or `maxPerBrand`. Baseline 3 is appropriate since the schema does the parameter work.

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: describe a UGC brief and get winning short-form video examples, with the concrete content of each result (hook, beats, remix template). It is unmistakably distinct from sibling generation tools like create_video or list_ad_formats.

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-to-use ('before writing a UGC script or a create_video brief') and a when-not/behavioral rule for weak results ('weak means no close match; say so instead of forcing one'). It also warns against word-for-word copying, which shapes how the output should be used.

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