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

With no annotations, the description carries the full burden, and it does add real context: the upstream source, its CC-BY-4.0 license, and the $0.25 USDC cost per call. It omits other behavioral traits an agent needs, such as whether name lookups are paginated, what a no-match result looks like, and how payment is authorized.

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 purpose, then returned fields, then concrete examples, then price – a sensible ordering with no filler. The dollar-cost clause is terse to the point of being abrupt, but it is information the caller needs before invoking a paid tool.

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 paid, seven-parameter tool with no annotations and no output schema, the definition covers the source, cost, and returned fields reasonably well. It falls short on the redundant input aliases and the limit parameter, which are exactly the ambiguities a caller would hit when constructing a request.

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 description coverage is 0% across seven parameters, so the description must compensate, and it only explains two of them (number and name) via examples. The alias parameters (q, ie, cro, company_number) and especially 'limit' are left entirely undefined, so an agent cannot tell which input form is canonical or how limit affects a name search.

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 ('Irish company lookup via CRO open data') with the data source named, and the country qualifier distinguishes it from the many sibling *_company tools. It also enumerates what comes back (legal name, status, type, dates, address), so an agent knows exactly what it is selecting.

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 by the two example invocations ({number:...} vs {name:...}), which show the two lookup modes. However, there is no explicit guidance on when to pick this over company_full, kyb_report, or the other country registries, and no statement about what happens when a name search matches many companies.

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