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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds extensive behavioral context beyond that: response segment structure, caching at KV level, the placeholder-slug filter, per-sport bias corrections, the 24h-move warning, and diagnostics for why segments might be empty. It also explains the fed_candidates exclusion and unreliable signals.

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 very long, dense, and uses all-caps segment names and bullets. It is front-loaded with the core purpose, but subsequent details (e.g., model family explanations, response structure) are verbose and could be trimmed. However, given the complexity and absence of an output schema, the length is partly justified.

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 must explain return values and it does so thoroughly, listing top-level fields (by_segment, fed_candidates, _diagnostics), the model families, and edge metrics. It also explains caching, knob effects, and why segments may be empty, providing a complete picture for an agent to correctly invoke and interpret the tool.

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 description coverage is 100% and each parameter already has a rich description (e.g., slippage_pp explains bid/ask context, min_partition_leg_kelly explains per-leg behavior). The description groups parameters into 'tradeable-edge knobs' and explains their interplay, but this is mostly redundant with the schema. It adds marginal value beyond what the schema already provides.

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 uses a specific verb ('Scan') and resource ('top Polymarket markets') with a clear outcome ('return opportunities where Pipeworx data disagrees with market price'). It also states the intended use case ('what should I bet on today'), distinguishing it from 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?

Clear context is given for when to use the tool, including its purpose to avoid paging hundreds of markets and its knob settings for filtering. It also provides a caution about fed bets being unreliable. However, it does not explicitly name alternative tools or say 'use instead of X', so it misses the top bar for explicit exclusions.

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