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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint:false. The description goes well beyond these by detailing model-family mechanics (e.g., per-sport α values), per-opportunity fields (edge_pp_net, kelly_fraction_half capped at 0.25), tradeable-edge knob behavior, 24h-move warnings, and KV-level caching (1h keyed on all knobs). It also surfaces edge cases like the unreliable Fed signal at meeting-month horizons. No contradiction with 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?

The description is long but highly dense and logically structured: model families are numbered, response segments are grouped, and the top-level response layout is provided. Every sentence carries unique domain-specific information (e.g., per-sport α, placeholder-slug filtering, diagnostics funnel counters). It could be slightly more scannable with headers, but there is no redundancy or filler.

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 knobs, three model families, no output schema), the description thoroughly compensates. It specifies the top-level response structure (by_segment, fed_candidates/fed_note, _diagnostics), lists exact per-opportunity fields, explains why segments can be empty, and documents filter interactions. An agent has enough information to invoke the tool and interpret its response without ambiguity.

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 descriptions for all 9 parameters, so the baseline is 3. The description adds meaningful beyond-schema context: it explains how min_partition_leg_kelly applies to basket legs rather than the parent level, why partition_overround parent kelly_fraction_half is always 0, how slippage_pp is deducted from raw edge, and the interplay of min_liquidity/max_spread_pp as tradeability filters. This lifts it above the 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+scope: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It clearly positions itself as an opportunity-discovery tool for daily betting, which distinguishes it from siblings like polymarket_arbitrage or polymarket_edge_tracker. The statement 'without paging hundreds of markets' adds practical value.

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 frames the use case ('what should I bet on today') and tells agents they can discover opportunities without exhausting pagination. It also explains when certain outputs appear (Fed candidates are excluded from ranking, diagnostics explain empty segments), but it does not explicitly name sibling tools or state when NOT to use this tool in favor of another.

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