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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat those. It adds valuable behavioral context: it walks the order book ladder, returns fill quality metrics (top_of_book, vwap_fill_price, slippage, etc.), and warns that partial fills convert arb into directional positions. This goes beyond the annotations, providing a clear picture of the tool's behavior.

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 well-structured with clear sections for each mode, bold for key terms, and front-loaded purpose and guidelines. While it is lengthy, the content is justified by the tool's complexity (two modes, multiple return fields). It could be slightly trimmed, but the structure is effective and information-dense.

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?

Given the tool's complexity (two modes, no output schema), the description comprehensively covers behavior, parameters, return fields, and risks. It lists all key return fields and provides usage warnings. The absence of an output schema is compensated by the detailed listing of return values. It is sufficiently complete for correct tool 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 100%, so baseline is 3. The description adds significant meaning beyond the schema by explaining the two modes, the default side logic for basket mode (auto based on partition sum), and the interpretation of size_usd differently for single-market vs basket. This deeper semantic context helps the agent use the parameters correctly.

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's function as a 'Realizable-vs-theoretical edge check against live CLOB order-book depth' and distinguishes it from siblings like polymarket_arbitrage and polymarket_edges by specifying exactly when to use it. It uses specific verbs and clearly delineates two modes: single-market and basket.

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 explicitly instructs: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It provides context on when theoretical overround is not capturable and warns about the risk of unhedged positions from partial fills, effectively guiding the agent on when to invoke this tool versus alternatives.

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