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

With no annotations present, the description carries the full burden and does well: it discloses the cost model and the no-result refund behavior, the source (ANAF filings), the language of the output (English), the currency (RON), and the sign convention (negative = loss). It stops short of stating read-only semantics explicitly, pagination, or any freshness/recency limits on the filings.

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 resource and scope, then a dense but purposeful field list, then a short billing sentence. The field enumeration is long but each item is information the agent may need; only minor trimming is possible.

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?

Absent an output schema, the description appropriately enumerates the returned metrics (turnover, revenue, expenses, profit, employees, assets, cash, debts, equity, plus derived ratios), which is exactly what the agent needs. It does not describe the response shape (per-year records) or how the derived ratios are reported, leaving a small gap.

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%, so both parameters (cui, years) are already documented with format examples and defaults in the schema. The description reinforces 'by CUI' but adds no format, range, or interaction detail beyond what the schema provides, so the baseline of 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?

States a specific verb+resource (annual financial statements filed with ANAF for a Romanian company by CUI) and enumerates exactly what data comes back. It is clearly distinguishable from siblings like get_company_risk_report, get_company_court_cases, or lookup_company, which cover different data domains.

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 implies usage (you call it to get financials for a company identified by CUI) and adds useful billing context ('costs 5 credits; not billed if nothing is found'), which influences whether an agent should call it. However, it never names alternatives (e.g., risk report vs. financials) or states when NOT to use it, so selection guidance is inferred rather than explicit.

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