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

With no annotations, the description carries the full burden of behavioral disclosure, and it delivers richly. It reveals the 100-per-page cap, cursor-based paging, the monthly ONRC snapshot limitation with the data_through check before declaring empty results, and the subtle default ordering behavior that affects newly registered companies.

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?

Every sentence earns its place: the opening sentence states core behavior, then parameter specifics, then a subtle edge case, then data-freshness context, and finally a routing instruction. Despite its length, it is dense with actionable guidance and front-loads the most important information.

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 12-parameter tool with no annotations and no output schema, the description is unusually complete. It covers ordering, paging, data freshness, parameter composition, and the correct alternative for aggregates. Minor gaps remain for status and numeric range parameters, but their names are largely self-explanatory and the description already gives enough context for an agent to avoid the most common pitfalls.

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%, so the description must compensate for all parameter meaning. It thoroughly explains caen_query, caen, judet, cui, sort, registered_after, and cursor, but leaves limit, status, min_turnover, min_employees, and registered_before undocumented, relying on parameter names alone. This partial compensation earns a mid-range score.

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, 'List companies matching a filter', and adds precise scope with 'largest turnover first, at most 100 per page'. It also differentiates from sibling company_stats by naming it explicitly as the aggregate alternative, so an agent can tell list_companies apart from related tools.

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?

The description gives explicit when-to-use guidance: 'If you want a count, an average or a total, use company_stats instead — do not page through companies to compute one.' It also provides concrete usage rules for specific parameters, including caen_query vs caen, judet spelling variants, the cui limit, and the sort/registered_after combination for newly registered companies.

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