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

Annotations already cover read-only and open-world behavior, but the description adds genuinely load-bearing details beyond them: cost ($0.02 per call), the payment mechanism (x402 USDC on Base via _meta, MPP on the HTTP URL), the fact that an empty result is still billed as a paid 200, name-based matching, and an explicit non-endorsement disclaimer. The one notable omission is that idempotentHint=false is never explained (e.g., repeated paid calls).

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?

All content is substantive, but it is delivered as one long run-on sentence led by billing mechanics, so the tool's actual purpose is buried mid-string and the disclaimer trails at the end. Dense but poorly front-loaded and hard to scan.

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?

An output schema exists, so return values need no explanation. Given that, the description covers everything an agent needs before calling: cost, payment path, data provenance, matching semantics, empty-result behavior, and legal caveats. Nothing material is missing.

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 the schema already documents employer, state, city, zip, limit and min_score in detail. The description only echoes the matching model ('matched by name', 'city and zip only narrow') and adds no format, matching-tolerance or score-threshold guidance beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource: 'Returns the OSHA inspections, violations and penalties on file for an employer in a state.' It also pins the data source (US Department of Labor inspection and violation files) and the output shape (establishments with a penalty roll-up), which cleanly separates it from sibling screening tools like sanctions_screen or exclusions_screen.

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 implied rather than stated: an agent can infer this is the OSHA/regulatory-labor lookup, and the description warns that an employer with no inspections yields an empty paid 200. However, it never names an alternative tool or an explicit when-not-to-use condition, so routing between this and the other screening tools is left to inference.

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