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

There are no annotations, so the description carries the burden. It adds meaningful behavioral context by warning that coverage.rows_with_metric is typically about half of coverage.matched_companies because many companies never filed the figure, and directs the agent to always report this alongside the answer. It does not fully explain all behavioral edge cases, but the disclosure is genuinely useful.

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 first sentence states the core operation, the second provides usage rationale, the third and fourth define key parameter options, and the last adds an important data-quality caveat. It is dense but not wasteful.

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 tool with 12 parameters, no output schema, and no annotations, the description covers the metric, group_by, and a useful coverage warning, but leaves many filtering parameters and the exact output shape unexplained. It is adequate for the core use case but not fully complete for nuanced calls.

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 schema has 0% description coverage, and the description compensates by enumerating valid metric values, group_by values, and an example years format. However, most of the 12 parameters (cui, caen, judet, status, caen_query, min_turnover, registered_after, year vs years) are still left to inference, so the compensation is only partial.

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 clearly states the tool computes a single aggregate number over a filtered population and enumerates the supported aggregations and metrics. It distinguishes itself from the sibling listing/search tools by explicitly saying to prefer it over listing companies and doing arithmetic manually.

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 gives explicit guidance on when to use this tool versus fetching and computing locally, and even provides a concrete group_by='year' example for time-series use. This gives an agent actionable decision criteria for selecting this tool over siblings.

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