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

With no annotations, the description carries the full burden and does disclose a lot: per-item inline errors rather than whole-call failure, a 25-item cap with a special 10-item UK sub-cap, the returned fields, and a $0.30 USDC price. Gaps remain on auth/payment mechanics, rate limits, and what happens when an entire jurisdiction block is malformed, but the operational picture is unusually clear.

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?

Front-loaded with the core purpose, then progressively denser detail (jurisdictions, output, limits, example, price, related tool). Every clause carries information, though the long jurisdiction enumeration mid-paragraph makes it a run-on that a bulleted list would have made scannable.

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 17-parameter tool with no annotations and no output schema, the description covers purpose, per-item error behavior, output fields, limits, identifier formats, an example payload, and pricing. Remaining ambiguity is minor: the meaning of "UK red flags" and whether non-UK results include equivalent flags is unspecified.

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 only 12% (only sg and us are annotated), so the description must compensate and largely does: it maps each country block to its identifier scheme (SIREN, CVR, Y-tunnus, UID, KRS, IČO, RPO, CRO, äriregister, UEN, ACN/ABN) and states the comma-separated format. The US STATE:ID format is explained with the collision rationale, and a concrete example object is given. Country-code-to-param mapping is implied by ordering rather than spelled out, which keeps it short of a 5.

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 ("verify ... companies in one call") plus the returned fields (name, status, type, dates, UK red flags). It enumerates exactly which schemes and jurisdictions are covered, which lets an agent distinguish it from the many single-jurisdiction siblings (uk_company, au_company, us_entity) without opening a 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?

The framing "up to 25 ... in one call" implies when to reach for the batch tool over per-record siblings, and it explicitly routes to /sanctions-batch for director/name screening. It also points to a free sample endpoint for evaluation. No explicit when-not-to-use (e.g. single-company lookups) is stated.

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