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

Beyond the read-only/idempotent annotations, the description discloses critical behaviors: Jaccard similarity threshold, placeholder filtering (>20% returns null), the response structure, and the FILL CHECK caveat with realizable_edge_pp ≤ 0 — explicitly warning not to trade. This is substantial non-obvious context.

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 front-loads purpose and usage in the first two sentences, then organizes supplemental details into labeled blocks (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). It earns its length given the tool's complexity, though tighter formatting would improve scanability.

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?

For a tool with no output schema and rich behavior, the description covers modes, outputs, filtering rules, fill-check caveats, and a pointer to a sibling for sizing. It fully equips the agent to decide and invoke the tool correctly.

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 covers both parameters, the description adds meaning beyond the schema: `event` walks child markets and runs partition_check; `topic` searches related events and flattens markets; it gives concrete slug/seed examples and explains output differences between modes. This far exceeds the high-coverage baseline.

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 statement: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly differentiates itself from siblings like polymarket_fill_risk and polymarket_edges by naming its distinct modes and explicitly pointing to another tool 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?

It explicitly states when to call with no args for trending_scan, when to use `event` vs `topic`, and recommends `event` for specific markets. It also notes that cross-event mode catches date-boundary patterns single-event misses, giving clear selection criteria.

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