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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond them: the exact data surface returned in a single aggregated call, and a concrete cost of 6 credits, which lets an agent weigh it against cheaper single-purpose calls. It omits error behaviour for invalid or non-existent company numbers.

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?

One dense, front-loaded sentence that leads with the verb and scope, followed by targeted audience and cost signals. The enumerated data list is long but each element is informative rather than filler; minor tightening of the colon-heavy list is possible but nothing is genuinely wasted.

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 high-complexity aggregation of roughly ten sibling tools with no output schema, the description does the necessary work by enumerating the returned data sections and the risk summary. With annotations covering the safety profile and cost disclosed, the main remaining gaps are error behaviour and result verbosity, which are secondary.

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 reads as 100%, but the actual schema descriptions are near-empty placeholders ('string, required'), so the description carries real weight. It establishes that companyNumber is a UK company registration number (format guidance the schema lacks) and that the director screen is against the disqualified register, matching screenDirectors. It does not flag that companyNumber is effectively mandatory despite the schema showing zero required parameters.

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 a specific verb and resource ('Full KYB check on a UK company number') and enumerates exactly what the aggregate covers: profile and status, officers, PSCs, overdue filings, charges, insolvency, disqualified-director screen, Gazette notices, plus a risk summary. An agent can immediately distinguish this from narrower siblings like company_officers or company_charges.

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?

It gives use-case context ('supplier onboarding, due diligence and anti-fraud') and signals the value proposition of aggregation with 'in one call'. However, it never routes the agent explicitly: it does not say when to prefer this over the individual sibling tools, nor does it exclude narrower use cases. Usage is implied rather than prescribed.

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