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

Annotations already carry readOnlyHint=true, and the description aligns with that. It adds behavioral context beyond annotations by identifying the authoritative government source and listing the returned data categories, which is useful for calibration.

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?

Three sentences, each earning its place: the first names the source and subject, the second lists returns, and the third states the business purpose. No filler or redundant restatement of the name.

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 no output schema, the description compensates by naming the expected return fields and use case. It is complete for a one-parameter read-only lookup, though it omits edge-case behavior (e.g., not-found handling), which is minor.

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% and the lone companyNumber parameter is already described with format guidance. The description's 'Given a UK registration number' adds no new semantics beyond the schema, so a mid-range baseline 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 opens with a specific verb+resource: 'UK company KYB lookup via the official Companies House register,' and enumerates concrete return fields. It explicitly scopes to UK registration numbers, distinguishing it from the sibling verify_us_company.

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 description states clear call context: 'to confirm a UK business is real, active, and who controls it, for KYB onboarding and counterparty due diligence.' It does not explicitly name a US alternative or state when not to use it, so it stops short of a 5.

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