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

Beyond the annotations (readOnlyHint, openWorldHint, destructiveHint), the description adds valuable behavioral details: pagination ('Up to 25 results per page with an opaque cursor'), the default year for financial filters ('single year, default 2024'), and the mandatory filter requirement. These are not inferable from annotations and significantly aid an agent in invoking the tool correctly.

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?

The description is composed of three focused sentences: the first states the core search/filter capability, the second explains pagination, and the third covers the year default and filter requirement. Every sentence earns its place with zero redundancy.

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 complex 15-parameter search tool with no output schema and no parameter descriptions, this description covers the essential behavior and constraints well. It explains the main filter dimensions, pagination, and year semantics. However, it does not specify the exact return value shape or format details (e.g., how to structure CAEN codes or locality names), leaving some ambiguity for the agent.

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?

With 0% schema description coverage, the description compensates effectively by mapping filter categories to parameters: name (query), CAEN activity (caen_code), county/locality (judet, locality), revenue/profit/employee ranges (min/max params), and VAT status (vat_registered). It also clarifies the 'year' parameter and cursor/limit pagination semantics, which the schema alone does not convey.

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's purpose: 'Search and filter the Firme Românești company directory' with specific filter dimensions (name, CAEN, county/locality, revenue/profit/employee ranges, VAT status). This specificity distinguishes it from sibling tools like get_company_profile or resolve_caen, which have different objectives.

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 provides clear context for when to use the tool: when searching or filtering companies, and it explicitly specifies 'Provide at least one filter.' However, it does not explicitly mention when not to use it or name alternatives, though the sibling tool names imply distinct use cases.

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