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

Annotations (readOnlyHint, idempotentHint, destructiveHint) are consistent with description declaring 'Read-only' and 'Live query to the official KAS register'. Adds context beyond annotations about the live nature and official source.

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?

Description is concise with no redundant information. Front-loads the main action, then provides usage guidance and return summary. Every sentence adds value.

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 simple two-parameter tool with no output schema, description mentions it returns 'VAT status and account-match result', which is sufficient. Covers purpose, usage, and behavior. Slightly vague on exact return format but adequate.

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 covers both parameters with descriptions (NIP and account). Description adds that account is optional and clarifies its purpose: checking if a given account number is registered to the company. This adds value beyond the schema.

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 it checks a Polish company's VAT status and optionally bank account registration, specifying the official register (Ministry of Finance white list). It distinguishes from sibling tools like check_risk_flags or get_company by focusing on VAT whitelist verification.

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?

Explicitly advises using this tool before paying an invoice, explaining the tax consequences of paying over PLN 15,000 to an unregistered account. Does not explicitly exclude other scenarios, but provides clear context.

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