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

Beyond the readOnly/idempotent annotations, the description discloses critical behaviors: caching ('Cached 1h at the KV level keyed on all knobs'), model-specific details (e.g., 'soft signal w/ halved Kelly', 'rare-by-design'), and diagnostic output ('_diagnostics... so callers can see WHY a segment is empty'). It also explains that Fed bets are excluded from ranking due to unreliable signals, adding transparency not conveyed by annotations.

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?

Despite its length, the description is densely informative and well-structured with clear section markers like 'FIVE MODEL FAMILIES', 'TRADEABLE-EDGE KNOBS', and 'RESPONSE TOP-LEVEL'. Every sentence contributes unique value—covering purpose, model details, output format, knob behavior, and caching—without redundancy, making it efficient for its 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?

With no output schema, the description fully explains the response structure: by_segment segments, fed_candidates/fed_note, and _diagnostics with funnel counters. It also covers edge calculation (edge_pp_net after slippage), risk metrics (kelly_fraction_half capped at 0.25), and filtering rationale (why segments can be empty), making the tool's behavior understandable even without an output schema.

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 covers all 9 params, the description adds substantial meaning beyond the raw property names. For example, it explains that min_kelly 'Skips opportunities that are too small to bet sensibly even if the edge is large', that min_partition_leg_kelly applies per-leg because 'Partition arbs always return kelly_fraction_half=0 at the parent level by design', and provides concrete defaults and their impact (e.g., 'Set to 5000 to drop thin-book opportunities'). This enriches the schema with domain context.

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 first sentence clearly states the verb and resource: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It also distinguishes itself from siblings by specifying the intended use case ('what should I bet on today') and by covering multiple model families across three segments, unlike focused sibling tools like polymarket_arbitrage or polymarket_fill_risk.

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 states the primary use case ('agents discover opportunities without paging hundreds of markets') and provides extensive guidance on how to configure knobs for different scenarios (e.g., 'Bump for very thin partitions; drop to 0 if you have a smarter fill model'). However, it does not explicitly exclude alternative tools or mention when not to use this tool, so it lacks explicit exclusions.

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