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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. Description adds context: 'walks child markets', 'checks date-axis/threshold-axis ordering', 'partition_check (sum of YES prices... deviations >3pp emit BUY/SELL EVERY LEG signal)', 'SEMANTIC ANCHOR using Jaccard similarity', 'PARTITION FILTER drops placeholder slugs', 'FILL CHECK against live CLOB depth'. No contradictions.

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?

Description is longer than typical but each sentence adds value. Structure is logical: overall purpose, three modes with detailed behavior, advanced features (semantic anchor, partition filter, fill check), and referral to sibling tool. Front-loaded with purpose. Could trim minor redundancy like 'Call with NO args' vs 'for a trending scan' but still efficient given 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?

No output schema, yet description fully explains response structure: 'opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)', 'partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}', and 'fill_check{theoretical_edge_pp_at_book, realizable_edge_pp at 1000 shares/leg, thin_legs[]}'. Covers edge cases like 'skipped_low_similarity' and 'placeholders_filtered'. Complete for a complex arbitrage detection 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% but description adds rich meaning beyond schema. For event: 'pass a Polymarket event slug... walks child markets, checks date-axis/threshold-axis ordering AND computes partition_check'. For topic: 'pass a seed question... searches related events, flattens markets, runs comparator on union. Cross-event mode catches patterns that single-event misses.' Schema only says 'event slug' or 'topic string'; description transforms these into actionable behavior.

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 finds arbitrage opportunities via 'monotonicity violations + partition-sum checks'. It distinguishes three modes: no args for trending scan, event for single-event mode, and topic for cross-event scan. The verb 'find' and specific resource 'arbitrage opportunities on Polymarket' make purpose unambiguous.

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 guidance: 'Call with NO args for a trending scan', 'event (recommended for a specific market)', 'topic for cross-event scanning'. It also explains when not to trade via fill check: 'realizable_edge_pp ≤ 0 means... do not trade it'. Alternatives mentioned: 'For custom sizing use polymarket_fill_risk'. This fully satisfies when-to-use and when-not.

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