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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior. The description adds substantial operational context: return fields with sources and confidence labels, explicit 'never guessed' handling of unknown facts, and scope limits such as no person, owner, or employee named and free mail providers yielding no company.

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?

The description is front-loaded with useful usage examples and is generally well organized. However, it spends multiple sentences explaining return values and confidence labels even though an output schema exists, and the 'no person' exclusion is repeated across the 'Companies only' and 'Do not use' clauses, which is mildly redundant.

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 one-parameter lookup with an output schema and full annotation coverage, the description covers purpose, usage, exclusions, and output meaning. Nothing needed to call the tool correctly is missing, and the output schema handles return structure.

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 single parameter is fully documented in the schema, including that email or website inputs are accepted and that only the part after @ is used. The description's 'Pass the domain' adds no new semantic detail beyond the schema, so the baseline 3 applies.

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 states a specific verb and resource ('Find the company behind a domain') and gives concrete examples such as 'which company is behind doctolib.fr?'. It scopes the tool to domain, website, or work-email inputs and excludes person, credit/risk, and no-public-record use cases, which separates it from generic registry or person lookups.

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 explicitly says when to use ('when the user has a company domain...') and when not to ('Do not use it for a person, for credit or risk...'). It also excludes free mail providers, sole proprietors, and companies with no public record, but does not name alternative sibling tools for those cases.

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