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

The description adds genuinely useful operational context beyond the annotations: it is a public endpoint, needs no API key, and consumes no API credits, which materially affects how an agent plans calls. But it describes a pure listing operation while the annotations declare readOnlyHint=false, an inconsistency the description does not reconcile; openWorldHint=false and destructiveHint=false are consistent with a static reference list. Because the mismatch is a conservative-annotation artifact rather than a false claim about mutation, this is a flag rather than an outright misleading description, but the conflict still leaves the agent unsure whether the call can change state.

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?

Two sentences, front-loaded with what is returned, followed by the access/cost note. Every clause carries information (returned fields, public access, no credits); no filler or restatement of the tool 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 input schema properties and no output schema, the description compensates by naming the returned fields (code, friendly name, description) and the cost/auth profile. For a trivial zero-parameter reference lookup that is essentially complete; only the readOnlyHint inconsistency leaves a loose end.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline applies. The description correctly implies a single unfiltered call with no inputs, and it instead spends its words on the response shape, which is the more useful information here.

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?

"List every company registration type that the VAT API may return" gives a specific verb (list) and resource (VAT registration/company type codes), plus the three fields returned (code, friendly name, description). An agent can distinguish this reference-data lookup from the sibling vat-api (which presumably validates or looks up VAT numbers) without opening any 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?

Usage is implied rather than stated: an agent can infer it should call this to resolve or enumerate VAT registration type codes, and the phrase "that the VAT API may return" hints it complements a VAT lookup call. However, there is no explicit when-to-use, no when-not-to-use, and no named alternative among the many siblings.

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