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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, and the description adds real context beyond that: a shared free daily quota (rate limiting), business-only scope with no personal data (privacy boundary), live source provenance per contact field, and which registries/sanctions lists are consulted. It does not say what happens when no website or registry match is found, which is the main remaining behavioral gap.

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 the core capability and the return contents before the usage sentence, with no filler. The field enumeration is a long, dense clause, but each item carries information an agent needs to decide relevance.

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 and no required parameters, the description correctly compensates by enumerating the returned profile fields and their provenance, and it states the cost/quota model and data boundary. What remains thin is failure behavior (no website found, no registry match) and the unexplained 'lang' option.

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 description adds genuine routing meaning by stating that domain is preferred and name is the fallback, going beyond the schema. However it only restates that city and country are 'optional', and the 'lang' parameter (en/fr enum) is unexplained in both the description and the schema, leaving one of five parameters with zero semantics and two with no added depth.

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?

Names a specific verb and resource ('Get a company's profile') and enumerates the returned data: what it does, industry, services, service area, address, phones/emails with source pages, social links, and official screening across registries and sanctions lists. This makes it clearly broader than the screening-focused siblings (sanctions_check, qc_licence, qc_contractor_check) even though they are not named.

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?

Gives explicit trigger conditions ('who a company is, how to contact it, or wants to research a prospect, supplier or partner') and input preference ('domain (preferred) or name'). It stops short of exclusion guidance, e.g. when to route a pure sanctions or licence query to sanctions_check or qc_licence instead of this broader call.

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