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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description concentrates on what they cannot express: the paid access model ('$0.01 per call (x402, USDC on Base, no account)') and the fact that ranking is computed from the latest balance sheet. It omits pagination or coverage caveats, but the payment/no-account detail is genuinely additive context an agent must know before calling.

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?

A single dense paragraph that front-loads cost, then usage, then behavior and return content. No filler sentences, though the pricing clause leads ahead of the actual purpose, which delays the primary framing slightly.

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 an output schema present, return values need not be spelled out, yet the description still summarizes the shape (top N, total with data, rank). Between annotations, full schema coverage and the output schema, an agent has everything needed to invoke this correctly.

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 100%, so the baseline is 3, but the description adds real semantics beyond the schema: it clarifies that the cui rank (rang_ref) is only reported 'if cui is given and in the top N,' which the schema's simpler 'rank within the list' does not convey. It also ties the code to a NACE-based activity code sourced from romania_company_profile.cod_caen.

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: 'ranks active Romanian companies with a given main CAEN code ... by turnover ... from their latest balance sheet.' The delimiting scope (by CAEN code, ranked by turnover) clearly separates it from siblings like romania_company_profile and romania_company_financials, which operate on a single company rather than an industry cohort.

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?

'Use when you need market leaders or competitors in a Romanian industry, or to place a company against its peers' gives a concrete triggering scenario. It does not, however, name an alternative tool or state when-not-to-use (e.g. for a single company's own financials use romania_company_financials), so routing is implied rather than explicit.

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