Search a platform

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

Annotations already cover readOnly, idempotent, openWorld and non-destructive, so the safety profile is settled. The description adds genuinely new operational context that annotations cannot express: 1 credit per call, failures are free, and cached repeats are free when max_age_days is used. Return shape and pagination behavior are not described, but no output schema exists so that gap is partly excusable.

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 verb and scope in the first sentence, followed by the platform list, the cost model, and the escape hatch. The trailing per-platform kinds list is dense and run-on but every element carries selection-relevant information, so little is wasted.

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?

With 8 parameters, a nested free-form params object, and no output schema, the description does the important work: it enumerates platforms, points to describe for underlying endpoint parameters, and discloses cost. Pagination semantics and the response payload remain undocumented, which is the main residual gap for an agent invoking it repeatedly.

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 description coverage is 100%, so the schema already explains kind, sort, limit, query, cursor, params and region, making 3 the baseline. The description adds some mapping value by listing which kinds exist per platform, but it does not clarify cursor paging, sort values, or that max_age_days lives inside the free-form params object.

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 (search), scope (one platform), and the resource set (posts, videos, users, other items) retrieved by keyword. It also enumerates the exact platform values and, critically, signals that this is a single-platform tool, which distinguishes it from the multi-target batch sibling.

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 bounds usage: 'one platform' and 'For anything beyond this, use the platform's own tool', which routes the agent away from this tool for advanced/edge cases. The kinds-per-platform breakdown gives concrete selection guidance, but it never names the batch sibling as the alternative for multi-platform searches, leaving that inference to the agent.

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