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

Annotations declare readOnlyHint, openWorldHint, idempotentHint as true and destructiveHint as false. The description adds substantial behavioral detail: the algorithmic checks (monotonicity violations, partition-sum), the fill check against live CLOB depth, semantic anchor (Jaccard similarity ≥0.30), partition filter (drops placeholder slugs), and output structure. No contradiction with annotations; it extends transparency beyond what annotations provide.

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 lengthy but well-structured: it opens with a clear purpose, then explains each mode, followed by algorithmic details, output format, and fill check. Every sentence adds value. Minor deduction for density—some details could be more succinct, but overall it's efficient for the complexity.

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 no output schema, the description explains the return structure (opportunities[] fields, partition_check fields, fill check fields). It covers key behaviors (semantic anchor, partition filter, fill check) and error indicators (skipped_low_similarity, placeholders_filtered). However, it lacks details on error conditions (e.g., invalid event slug) or rate limits. Still, it is remarkably complete for a complex 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?

Schema coverage is 100% (both parameters have descriptions). The description adds rich meaning: for 'event', it specifies the format (slug or URL) and explains the inner workings (walks child markets, checks date-axis/threshold-axis ordering, computes partition_check). For 'topic', it describes cross-event scanning and the Jaccard similarity requirement. 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 explicitly states the tool's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It distinguishes three modes (no args, event, topic) with clear use cases, and the verb 'find' and resource 'arbitrage opportunities' are specific. The description is unique among siblings (e.g., polymarket_edges, polymarket_fill_risk) and does not overlap.

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 explicit guidance: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', 'topic (for cross-event scanning)'. It explains what each mode does and when to use them. It also states when not to trade ('realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it') and references sibling polymarket_fill_risk for custom sizing.

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