add_manual_invoice

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

With no annotations, the description carries the full burden. It does disclose one important behavioral fact — that no document is generated and an existing PDF must be supplied — but says nothing about duplicate invoice numbers, idempotency, validation, required permissions, or whether the record links back to the import issue.

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?

A single sentence with the action front-loaded and the qualifying condition immediately after it. No filler, and the parenthetical carries real disambiguating information rather than restating the name.

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 10-parameter write tool, the description supplies the workflow context an agent needs (import failure, pre-existing PDF) while the schema fully documents parameters and an output schema covers the return. Only edge-case behavior such as duplicate numbers or failure modes is unaddressed.

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%, including nested LineInput fields with Czech explanations for unit, quantity, VAT rate, and net unit price. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 applies.

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 and resource ("Zapíše do evidence vydanou fakturu") and adds a distinguishing clause: the invoice is one the import could not read and the PDF already exists, so nothing is generated. That separates it from issue_invoice, which produces a PDF, though it never names that sibling directly.

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 when-to-use condition is explicit and narrow: only for issued invoices that the import failed to parse, with an existing PDF. The parenthetical "nic se generuje" implicitly rules out the generation path, but no alternative tool is named and no explicit when-not case is given.

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