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

With no annotations, the description carries the full burden and delivers substantive behavior: the change-field enumeration, the GDPR-driven restrictions for natural persons (only three fields returned, masked account numbers with a concrete example, name forced to null), and the API-key requirement. It omits operational traits such as rate limits, pagination, or ordering/deduplication of results, keeping it short of a 5.

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 purpose is front-loaded in the first sentence, and the following sentences each add distinct value (field list, natural-person caveats, polling role, auth). It is dense but not padded; minor parenthetical detail (the mask example) could be trimmed.

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?

There is no output schema and no annotations, so the description must explain returns; it does so by naming the fields returned and the natural-person exceptions. It leaves the shape of the change payload (one entry per change, IDs, timestamps) and polling mechanics unstated, so it is strong but not fully self-sufficient.

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%, so 'since' and 'api_key' are already documented and the baseline is 3. The description restates the since default and the optional api_key, and notably references a 'field' property with enum values that is absent from the input schema, which adds detail but no actionable parameter guidance.

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 states a specific verb (return changes) with explicit resource (VAT status, bank accounts, registry data from the White List), scope (since a given date for the NIPs you monitor), and enumerates the possible change types. This clearly differentiates it from siblings like sprawdz_nip or sprawdz_rachunek, which are point lookups rather than change feeds.

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?

It gives strong usage context with 'A polling channel for agents' and routes one related need elsewhere ('check a specific account with sprawdz_rachunek'). It also states the API key prerequisite. However, it never states when NOT to use this tool (e.g. versus observe_nip/list_observations for setting up monitoring), so a small gap remains.

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