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

Annotations only declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds substantial behavioral detail beyond that: threshold for partition deviations (>3pp), Jaccard similarity anchor (≥0.30), placeholder filter (20%), and the fill check (theoretical vs realizable edge, 'do not trade it' when realizable ≤0). It also discloses that the tool internally calls arbitrage.fill_check against live CLOB depth. No contradiction with annotations.

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 dense and lengthy, but it is logically structured with labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded with the primary purpose and mode selection. Every sentence conveys useful information, so while it's not perfectly concise, it earns a 4 for effective organization and no wasted words.

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 (three modes, multiple checks, fill risk), the description is remarkably complete. It describes the response structure (opportunities[] with fields, partition_check fields, skipped_low_similarity count) and the FILL CHECK output. With no output schema present, the description carries the full burden and meets it well.

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?

Even though schema coverage is 100%, the description greatly enriches parameter meaning. For `event`, it explains that the tool 'walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check.' For `topic`, it details the cross-event search and flattening process. It also gives concrete example slugs and notes that full URLs are accepted. This goes far beyond the schema's one-line 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: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly identifies the tool's function and distinguishes among three modes (trending_scan, event, topic), with concrete examples and recommendations. This fully differentiates it from siblings like polymarket_fill_risk.

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?

Explicit usage guidance is provided: 'Call with NO args for a trending_scan... pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan.' It also states when to prefer one mode over another (event recommended for a specific market) and names an alternative tool: 'For custom sizing use polymarket_fill_risk.' This is exactly the kind of when-to-use vs. alternatives guidance that earns a 5.

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