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

Annotations already mark this as read-only/idempotent, but the description goes far beyond by disclosing caching behavior ('Cached 1h at the KV level keyed on all knobs'), methodology details (lognormal barrier, GDELT ratio, per-sport bias correction), response structure, and important caveats like the Fed signal unreliability. It also warns about 24h price moves and diagnostics for empty segments, giving the agent a full picture of behavior and side effects.

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 and dense, but it is front-loaded with a one-sentence purpose and then logically organized into sections (model families, structural arbitrage, concentrated longshot, knobs, response, diagnostics, caching). Every sentence contributes substantive information, though the sheer volume could overwhelm. Given the tool's complexity, the length is justified, but it is not as succinct as the highest bar.

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?

There is no output schema, so the description carries full responsibility for explaining what the tool returns. It thoroughly describes top-level fields (by_segment, fed_candidates, _diagnostics), the contents of each segment, filter behavior, and potential causes for empty results. It also covers caveats like the Fed note and cache behavior, making it highly complete for an agent to invoke correctly and interpret results.

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 schema coverage is 100%, the description adds essential operational meaning beyond raw definitions. It explains how slippage_pp interacts with edge calculation and Kelly sizing, why min_kelly doesn't apply to partition overrounds, and how min_partition_leg_kelly filters per-leg Kelly. It also gives concrete recommended values (e.g., max_spread_pp=2, min_liquidity=5000) and contextualizes them with market microstructure facts. This greatly enhances parameter understanding.

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 opening sentence clearly states the tool's function: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' This is a specific verb+resource combo that distinguishes it from siblings like polymarket_arbitrage or polymarket_edge_tracker by focusing on model-driven, structural, and longshot opportunities. The added 'what should I bet on today' framing further clarifies its intended niche.

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 explicitly positions the tool for daily bet discovery ('Built for "what should I bet on today"') and explains when to use knobs like min_liquidity and max_spread_pp to filter for tradeable edges. It does not name alternative sibling tools or state explicit 'when not to use' scenarios, but the use case and behavior are clear enough to guide an agent.

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