prediction_search

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

No annotations are provided, so the description carries the disclosure burden. It reveals the tool only scans the most active markets, not all markets, and that matches in the question rank higher. This gives agents a realistic view of result completeness and ordering without overpromising.

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?

The description is efficiently structured: a one-sentence purpose, then an Args block, then two high-value behavioral notes. Every sentence adds information, and the content is front-loaded with the action. It is slightly longer than ideal but avoids redundancy.

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?

The tool's complexity is low (2 params) and an output schema exists. The description covers purpose, parameter semantics, ranking, and data scope limitations. It doesn't explain what 'active' or 'most active' means, but that's a minor gap given the output schema likely reveals results.

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%, so the description must explain parameters. It defines query with examples ('fed rate', 'bitcoin 100k') and limit as 'Matches to return', adding meaning beyond the schema. However, it omits details like default/max limit or case sensitivity, which the schema partially covers via default.

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?

The description clearly states the tool searches active prediction markets by keyword, with a specific verb and resource. It distinguishes from sibling tools like prediction_markets (listing) and search_symbol by focusing on keyword search over prediction markets. The examples clarify the intended use.

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 description provides context that Polymarket lacks server-side search, so this tool scans the most active markets, setting expectations for coverage. It explains ranking behavior (question matches above description) but does not explicitly name alternatives or when-not-to-use. This is clear context without explicit exclusions.

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