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

With zero annotations, the description carries the full burden and does most of it: it discloses what data sources are combined, that the domain step is optional, that the output is a categorical trust flag with its four possible values, and that it is not a regulated KYC/AML result. It omits failure behavior, what happens when no record is found, and latency/rate characteristics of the paid call.

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 primary use case and core data sources, then scope caveat, then example, then pricing and related tools. Nearly every clause is informative, though the dense pricing/related-tools tail is closer to a menu than to tool documentation and slightly competes with the core description.

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 no-annotation, no-output-schema tool this description does substantial work: it names the output shape and its enum values, the bundled sources, the cost, and the alternatives. The remaining gap is parameter-level input rules given 0% schema coverage, which is the one thing an agent could still get wrong.

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 0% and all three parameters (name, domain, number) are undocumented in the schema, so the description must compensate. The example payloads clarify that number alone or name+domain are valid shapes and imply domain drives the RDAP/website skim, but it never specifies required formats, whether number must be the 8-digit Companies House form, or what happens if both name and number are supplied.

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 (UK due-diligence job) and enumerates the exact inputs bundled: Companies House pack, public sanctions on entity and active officers, and optional domain RDAP/website skim, plus the output (a trust flag with named values). It explicitly positions itself between the siblings uk_company and kyb_report, so an agent can discriminate 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?

Gives an explicit use case (UK-only due diligence), scope exclusions (screening only, not regulated KYC/AML), price-tier positioning versus uk_company and kyb_report, and named alternatives for adjacent jobs (/kyb, /uk-watch, /sanctions, /uk-company-lite) with their prices. This is genuine routing guidance rather than implied usage.

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