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

Goes well past the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing that saving can auto-submit to KSeF and that this is legally binding, that invoice numbering is sequential, that default company data is used without department_id, and that a Cotlet API key with app access is required. These are exactly the side-effect and prerequisite facts an agent needs before mutating state.

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?

Front-loaded with purpose and line formats, then legal/auth caveats. Slightly marred by redundancy: confirmation is stated twice ('By default you confirm each call' and 'confirm with the user before each call'), and the Cotlet API key sentence reads as boilerplate.

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 an 8-parameter write tool with full schema coverage and a safety-carrying annotation set, the description covers the mutation's side effects, defaults, and prerequisites. It stops short of describing what comes back (no output schema exists, so an invoice id/number return hint would have completed it).

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 coverage is already 100%, so baseline is 3, but the description adds semantic meaning beyond the schema: it explains the two alternative line shapes for 'positions' and states the fallback behavior when department_id is absent, which the schema description does not say. It does not cover kind or date defaults beyond what the schema already gives.

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 ('Issue an invoice for a client with products or free lines') and clarifies the persistence behavior ('Saves an invoice with the next number in your series'). It implicitly separates creation from the sibling send/pay tools, but never names an alternative, so it falls short of the explicit sibling-differentiation bar.

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 useful operating context (default company data when department_id is omitted, per-call confirmation, user consent required before calls) but never states when to choose this tool over siblings such as fakturownia_send_invoice_to_ksef, fakturownia_send_invoice_email, or fakturownia_mark_invoice_paid. Usage is implied rather than routed.

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