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

The description goes far beyond the readOnly/openWorld/idempotent annotations, disclosing caching behavior ('Cached 1h at the KV level keyed on all knobs.'), response structure with diagnostics for empty segments, and nuanced caveats (e.g., the 24h-move warning when recent price movement already exceeds the edge). It also explains why partition_overround opportunities carry a parent-level kelly_fraction_half=0, which is not obvious from annotations alone.

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 every sentence carries substantive information about model families, response segments, filters, and diagnostics. It is structured with clear uppercase headers (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT, TRADEABLE-EDGE KNOBS, RESPONSE TOP-LEVEL) and front-loads the core use case. It is not as tight as a two-sentence ideal, but the length is justified by the tool's 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 the tool's complexity (9 parameters, no output schema), the description is remarkably complete. It explains the return structure (by_segment, fed_candidates, _diagnostics), how to interpret empty segments (funnel counters show why), and even the reasoning behind unreliable Fed signals. The absence of an output schema is compensated by a thorough prose description of what callers will receive.

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?

The input schema already provides 100% parameter coverage with clear descriptions, so the baseline is 3. The description adds value by explaining the rationale behind knobs: 'min_liquidity / max_spread_pp drop opportunities where edge isn't realizable', and it clarifies a subtle interaction—min_kelly never filters partition arbs because they use per-leg Kelly instead. This extra context helps agents choose values correctly beyond what the schema states.

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 states a specific verb+resource+scope: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It also distinguishes itself from siblings by enumerating the five model families and the built-for use case ('what should I bet on today'), making clear what kind of edge detection it performs that other tools might not.

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 clear context for when to use the tool: when agents want a curated list of opportunities without paging through hundreds of markets. It gives concrete knob-setting examples (e.g., setting min_liquidity to 5000 to drop thin-book opportunities) and even explains when the Fed signal is unreliable. However, it does not explicitly name alternatives or state when not to use this tool versus a sibling like polymarket_arbitrage.

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