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

With no annotations, the description carries full burden and excels. It discloses critical field semantics: 'Position Value USD is current marked value, not final payout at resolution' and 'Cost Basis USD and Unrealized PnL USD apply to the displayed row only — not the wallet's total PM activity.' This prevents misinterpretation and goes beyond generic descriptions.

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 concise and well-structured, with a purpose statement, a bullet list of key fields, and a prerequisites section. Every sentence adds value, and the most important context is front-loaded.

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 output schema reduces the burden for return values, and the description covers output field semantics well. However, the input structure is left ambiguous: it does not state whether the position is for the authenticated user or an address, and the marketId acquisition is inconsistent (the schema says prediction_market_screener, the description says prediction_market_lookup). This leaves gaps in what the API expects.

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% for the top-level parameter, and the description does not explain the `request` object or its fields at all. The only parameter-related guidance is the prerequisite to call prediction_market_lookup, but it does not describe how to construct a valid request or what `marketId` should look like. The schema itself has nested descriptions, but the description adds little beyond that.

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 opens with 'Detailed position breakdown for a Polymarket market,' which specifies the verb (breakdown) and the resource (position in a Polymarket market). It distinguishes from sibling tools like prediction_market_orderbook and prediction_market_address_pnl, though it does not clarify whose position (e.g., the authenticated user) is returned, preventing a perfect score.

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 an explicit prerequisite: 'If marketId is unknown, call prediction_market_lookup first.' This gives clear when-to-use context and points to a sibling tool. However, it does not explicitly state when not to use this tool versus other position-related tools, such as prediction_market_address_pnl.

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