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

Beyond the read-only/idempotent annotations, the description discloses substantial behavior: 1h KV caching keyed on knobs, the three-model family grouping, per-sport bias correction with alpha values, placeholder-slug filters, tradeable-edge gates, diagnostics so callers can see why segments are empty, and reliability caveats for Fed signals. It also reveals that partition arbs return kelly_fraction_half=0 at the parent level by design, which is critical for correct invocation.

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 well-structured with clear header-like segments in ALL CAPS (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT, TRADEABLE-EDGE KNOBS, RESPONSE TOP-LEVEL) and is front-loaded with the core purpose. Every sentence contributes useful information, though the sheer volume could be trimmed for lighter-weight scenarios.

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?

For a complex 9-parameter tool with no output schema, the description is remarkably complete: it specifies response top-level fields (by_segment, fed_candidates/fed_note, _diagnostics), explains model families and their logic, notes caching, and clarifies why Fed bets are excluded from ranking. This gives an agent enough context to select, invoke, and interpret results correctly.

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?

Schema coverage is 100%, but the description adds significant meaning beyond the schema: it explains the 'TRADEABLE-EDGE KNOBS' section, documents parameter interactions (e.g., min_kelly never filters partition_overround because parent-level half-Kelly is always 0; min_partition_leg_kelly applies per-leg instead), and provides rationale for defaults (slippage assumptions, liquidity thresholds). This goes well beyond baseline for high schema coverage.

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: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It clearly articulates the tool's intended use and differentiates from siblings by name-dropping specific model families (crypto_price, news_momentum, partition_overround, concentrated_longshot) and behavioral traits like 'rare-by-design' and 'filters partitions.'

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 includes an explicit use case: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It does not explicitly name alternatives or state when not to use it relative to sibling tools, but gives a clear context and even notes exclusions like Fed bets being surfaced but excluded from ranking.

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