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

Adds useful facts beyond the annotations: the check is free, limited to one register per call, and subject to per-register preconditions. It does not disclose token consumption, whether results are cached, or what a failed/partial check looks like, which matters given readOnlyHint=false and openWorldHint=true.

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 sentence that front-loads the key qualifier ('Bezplatně', one register) and then parenthesizes the per-register caveats. No filler.

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 no output schema, the description should set expectations for what comes back from a check (result shape, whether a token is consumed, partial failures), and it doesn't. The input side is well covered, the output side is not.

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?

The 'register' enum has no per-value descriptions in the schema, and the description is the only place explaining what each of the five values actually returns. It also clarifies that 'cislo_op' is only used for 'doklad' - a constraint not expressible in 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?

States a specific verb and resource ('Bezplatně ověří jeden rejstřík u prověrky') and enumerates the five registers precisely, so the agent knows exactly what is checked. It doesn't differentiate itself from siblings like check_person or get_report, which keeps it short of a 5.

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 concrete per-register conditions: 'doklad' requires a document number, 'dph' only works for IČO or birth number, and 'katastr' is limited to own property. It does not say when to prefer this over check_person/get_report, but the register-scoping guidance is clear context.

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