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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the required OAuth scope, the explicit instruction never to ask the user for a KSeF token or password, and the boundary that no new invoices are downloaded — all auth/scope behavior the schema cannot express.

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?

Three short sentences, each carrying distinct information: what is returned, the auth precondition, and the scope boundary. Front-loaded with the resource and its fields, 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?

An output schema exists, so return values need no prose explanation, and the auth/scope requirements are fully stated. The only meaningful gap is the unaddressed `limit` parameter and any notion of result truncation, which matters for a listing tool capped at 200.

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?

There is one parameter, `limit`, with 0% schema description coverage and a maximum of 200, and the description never mentions it. It does not explain that the result set is capped, what the default is, or whether ordering/paging applies, so the description does nothing to compensate for the schema gap.

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 ('List cost invoices already stored on the linked KSeF Płatności account') and enumerates the returned fields, which lets an agent distinguish it from report/analysis siblings like unpaid_due_soon or payment_audit_report. It stops short of naming a sibling it is not, relying on the negative clause about downloading from KSeF for differentiation.

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 a clear precondition (requires OAuth scope invoices.read) and an explicit exclusion ('Does not download new invoices from KSeF'), which tells the agent this is a read of already-synced data. It does not say which sibling to use when the user actually wants to fetch new invoices, so guidance is clear but not complete.

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