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

With no annotations, the description carries the full burden and does well: it discloses the search implementation (Postgres FTS + trigram), the empty-result contract (200 with a category suggestion), the returned fields (slugs, blended probabilities, match confidence), and the cost/payment model ($0.02 via x402). Auth and rate-limit behavior are not stated, keeping it out of the top band.

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-loads the core purpose in the first clause, then layers operational detail. There is mild redundancy ('returns slugs for other endpoints' and 'Returns slugs, blended probabilities'), and the bracketed HTTP/price/docs metadata is dense, but nothing is wasted overall.

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?

In the absence of annotations and an output schema, the description supplies a strong behavioral picture: return values, edge-case behavior, and cost. The one meaningful omission is parameter meaning, which leaves the definition slightly incomplete for fully correct invocation.

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 0% and the description never mentions any of the three parameters. The 'free-text query' phrase loosely maps to q, but the required limit and the category enum (with its seven valid values) receive no explanation, so the description fails to compensate for the coverage gap.

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 ('Find prediction markets by free-text query') and clarifies its role as a discovery front-end returning slugs for other endpoints, which implicitly differentiates it from retrieval tools like probability_get. It stops short of naming a sibling outright, but an agent can still tell what it does without opening the schema.

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?

The phrase 'by free-text query' implies when to reach for it, but there is no explicit when-not guidance or named alternatives among the many probability_board_*, probability_calendar_*, and probability_movers_* siblings. Usage 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.