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

Goes well past the annotations: pricing ($0.002/call via x402 USDC on Base, no account), a free tier of 3 calls per IP per UTC day with the MCP/HTTP flag distinction, and result-set behavior (up to 30 matches, active companies sorted first). Those are exactly the operational facts an agent needs and cannot get from readOnlyHint/idempotentHint.

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?

Three dense sentences with no filler, and the free-tier detail is actionable. It loses a point only for front-loading pricing/access before the actual purpose, so the core identity is in the second sentence rather than the first.

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 read-only lookup with a 100%-covered one-param schema and an output schema present, nothing essential is missing. It even over-delivers by summarizing the returned fields and ordering, which the output schema would not tell the agent about ranking.

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% for the single param, so the schema already documents the accepted formats, the RO-prefix optionality and the J40/123/2020 example. The description restates the same facts without adding syntax, normalization or matching behavior beyond them; baseline 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 ('Romanian company lookup / search in the Romania trade register (ONRC)') and enumerates the accepted key types (nume, CUI/CIF, J-number). It also distinguishes itself from siblings by naming the downstream use ('need its CUI for the other tools'), so an agent can place it relative to romania_company_profile or romania_company_risk_kyb.

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?

Gives an explicit trigger: 'Use when you have a Romanian company name and need its CUI... or to verify a CUI exists.' That is a clear when-to-use, but it never states when not to use it or names a sibling alternative for cases where a full profile/financials is actually wanted.

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