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

The description goes far beyond the annotations (which declare it read-only, open-world, idempotent, non-destructive). It details internal logic (e.g., 'lognormal barrier from 90d FRED log-returns', 'favorite-longshot bias correction with per-sport α'), caching behavior ('Cached 1h at the KV level'), and response structure including diagnostics. This level of transparency ensures the agent understands exactly what the tool does and its limitations.

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 comprehensive but overly verbose. It contains detailed model explanations that, while important, could be streamlined. The structure with sections (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) helps, but the density of technical terms (e.g., 'favorite-longshot bias correction', 'placeholder-slug filter') may hinder quick comprehension. A more concise summary with pointers to additional details would improve efficiency.

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, nested logic), the description covers all necessary aspects: input parameters explanations, internal model details, response structure (by_segment, diagnostics, fed_candidates), and caching behavior. It even explains edge cases ('your edge may already be in the price' warning). This completeness allows an agent to use the tool effectively without additional context.

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?

Since schema coverage is 100%, the baseline is 3. The description adds significant value beyond the schema by explaining the rationale and interactions between parameters (e.g., why min_kelly does not filter partition arbs and how min_partition_leg_kelly compensates, the effect of slippage_pp on edge calculation). This extra context justifies a score above 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 clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It explicitly targets the 'what should I bet on today' use case and distinguishes itself from other tools by avoiding paging through hundreds of markets. The three response segments (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) are well-defined, giving the agent a precise understanding of the tool's capabilities.

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 guidance on when to use the tool (discovering betting opportunities with conflicting data) and explains the 'tradeable-edge knobs' (min_liquidity, max_spread_pp, etc.) to filter results. It also notes that Fed candidates are excluded from ranking due to unreliable signals. However, it does not explicitly state when not to use this tool versus siblings like polymarket_arbitrage or polymarket_edge_tracker, which would strengthen the guidance.

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