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

Annotations already declare readOnlyHint, idempotentHint, and non-open-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the content is year-pinned to 2026, it explicitly documents non-modelled cases, and it lists official sources. It does not describe the shape of the returned content, but for a zero-param reference tool that is a minor omission.

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?

Two short sentences, front-loaded with what the tool contains, then the call-to-action. Every clause carries information (scope, options, gaps, sources). The only softness is the hedged closing phrase 'may not cover', which is less decisive than it could be.

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 zero-parameter reference tool with no output schema, the description covers what an agent needs: subject matter, year scope, limitations, and sources. It does not clarify whether the answer is a static document or a queryable summary, which is the one gap worth noting.

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 tool takes no parameters, so the baseline is 4 and there is nothing for the description to compensate for. It correctly implies the tool is a no-input lookup by not suggesting any filtering options.

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 the resource precisely: the Polish tax rules the calculators apply (2026), the options they accept, what is not modelled, and the official sources. That is enough to distinguish it from calculation siblings like net_salary or employer_cost. It stops short of naming the operation explicitly (e.g. 'returns a reference page'), which keeps it from 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?

It gives a clear trigger: 'Call it before answering a question the other tools may not cover,' which tells the agent to consult it ahead of uncertain queries. The condition is somewhat soft ('may not cover') and it does not enumerate which sibling tools have known gaps, leaving the agent to judge coverage itself.

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