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

With readOnlyHint/destructiveHint already covering the safety profile, the description adds genuinely new behavioral facts: the call is paid in USDC on Base, spoofing detection is out of scope, and defaults (5.0% impact bound, 10.0% haircut) apply. It does not describe latency, rate limits, or failure modes when a slug fails to resolve, which keeps it below 5.

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 core metric is front-loaded in the first sentence, followed by three short, load-bearing sentences for the out-of-scope boundary, input resolution, and payment. The opening sentence is dense and requires a second read, which costs it the top score, but there is no 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?

For a 6-param tool with an output schema (so return format needn't be explained), the description covers the metric definition, defaults, identifier resolution, cost, and scope exclusions. The one gap is precedence when both token_id and market_slug are supplied, and the description omits any note about the paid-call cost relative to parameter choices.

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%, so the baseline is 3, and the description clears that bar by documenting a cross-parameter relationship the schema does not state: token_id and market_slug(+outcome) are alternative resolution paths, with outcome only meaningful in the slug case. The default values it cites duplicate the schema, but the resolution-path clarification is real added meaning.

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 names a precise metric (executable depth within a price-impact bound, before and after a top-of-book haircut) on a specific resource (a single Polymarket outcome), and the 'before vs after haircut' framing separates it from plain depth/liquidity siblings such as prediction.exit_capacity_audit. An agent can tell exactly what number it is asking for without opening the schema.

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?

Usage context is clear (modeling the risk that the best resting order is cancelled before you trade), and it explicitly states a boundary: 'Does not detect or flag actual spoofing (out of scope)'. It also explains that either an identifier input path (token_id) or a resolution path (market_slug + outcome) is accepted. It stops short of naming a specific sibling tool to use instead for any case, so it does not reach a 5.

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