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

With no annotations, the description carries the burden. It responsibly discloses the returned change types, enumerates possible field values, notes the API key requirement, and frames the tool as a polling mechanism. It stops short of describing response shape, pagination, or prerequisite monitoring state, but adds meaningful behavioral context beyond the schema.

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 two sentences, starts with the core action and resource, and packs the key field enum and auth requirement into a compact second sentence. Every sentence earns its place with no filler or repetition.

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?

The tool has no output schema and no annotations, so the description must cover return semantics and prerequisites. It explains the change categories and field property, but does not state the expected response container, pagination/limits, or that NIPs must first be monitored via observe_nip. Adequate but with meaningful gaps.

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 schema already documents both parameters (since and api_key) with 100% coverage, so the baseline is 3. The description adds light context by mentioning 'since a given date' and the API key, but does not materially improve on the schema's parameter documentation.

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 uses a specific verb ('Return') and names exact resources: VAT status, bank accounts, registry data (name, address, KRS, REGON) from the White List. It also ties the operation to monitored NIPs and a since-date, which clearly distinguishes it from generic 'change' tools and from sibling lookup tools like sprawdz_nip.

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 gives clear context: it is 'a polling channel for agents', so an agent can infer it is appropriate when actively checking for changes rather than receiving push notifications via set_webhook. It also states the API key requirement. However, it does not explicitly name alternatives or state when not to use the tool.

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