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

Beyond the read-only/idempotent annotations, the description discloses rich behavioral details: the partition filter drops placeholder slugs, deviations >3pp trigger signals, skipped_low_similarity reports rejection count, and the fill check prices against live CLOB depth with a clear 'do not trade it' instruction when realizable_edge_pp ≤ 0. No annotation contradiction; this significantly extends trust and safety understanding.

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 long but every section (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) earns its place with dense, relevant information. It is front-loaded with the core purpose and immediately explains invocation modes, then layers behavioral details in a logical order without repetition or fluff.

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 no output schema, the description fully compensates by enumerating response fields (opportunities[], partition_check, fill_check) and explaining edge cases (skipped_low_similarity, placeholders_filtered, thin_legs). It covers a complex multi-mode tool exhaustively, including failure interpretation and interaction with a sibling tool.

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?

Although the schema already describes both parameters at 100% coverage, the description adds substantial semantic depth: it explains what each mode does, that event accepts slugs/URLs, that topic accepts seed questions, that no args triggers trending_scan, and gives concrete examples. This goes far beyond the schema's field descriptions.

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 a specific verb+resource+method: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes this from siblings like polymarket_edges and polymarket_fill_risk by describing unique modes (trending_scan, event, topic) and explicitly referencing a sibling for custom sizing.

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?

Usage guidance is explicit and comprehensive: 'Call with NO args for a trending_scan,' 'pass event,' and 'pass topic.' It provides a recommendation ('event ... recommended for a specific market'), explains cross-event advantages, and even tells the agent when to use a sibling tool ('For custom sizing use polymarket_fill_risk').

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