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

Annotations only cover readOnlyHint and openWorldHint, and the description adds materially: it discloses the commercial model ($0.005 USDC per successful call, x402 on Base/Solana/Arc) and that failed calls are not charged, which is critical behavioral context for a paid endpoint. It also discloses data provenance (official record link per case) and a name-match reliability caveat. What it omits is result-volume behavior such as pagination or how many records typically come back.

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 resource and sources are front-loaded before filters, caveat, and pricing, which is the right ordering for an agent scanning for relevance. It is dense but nearly every clause carries information; the only soft spot is a slightly run-on construction in the first sentence packing sources, filters, and the record-link detail together.

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 an output schema present, return shape need not be explained, and the description covers provenance, payment mechanics, and legal interpretation. For a 6-parameter, no-required-args search tool this is close to complete; the missing piece is any hint about default result behavior (the schema's limit default of 20 is never surfaced in the description).

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%, so every parameter including enum-like values for 'source' (osha, epa, osha,epa) is already documented. The description restates the filter names in prose and adds no syntax, format, or interaction detail (e.g. how minPenalty interacts with EPA cases, which often lack penalties) beyond the schema. Baseline 3 is appropriate.

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 the specific resource (US workplace and environmental enforcement cases) and its two upstream sources (US Department of Labor API for OSHA inspections, EPA ECHO), plus the filterable dimensions. That is far more than a restatement of the tool name 'violations'. It does not, however, distinguish itself from the sibling 'enforcement_actions' or 'screen_debarment', which an agent could plausibly confuse it with.

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 is implied by the filter list (look up a company's OSHA/EPA records by name, state, date, or penalty floor), and the legal caveat 'matched by name, not a finding of guilt' signals the appropriate interpretive context. There is no explicit when-to-use / when-not-to-use statement, and no routing to the overlapping 'enforcement_actions' sibling.

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