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

The destructiveHint annotation signals a mutation, but the description goes far beyond it: no draft state, immediate issuance, consumption of the next number in the series, and a remediation path ('delete or cancel it in Vyfakturuj if wrong'). It further discloses that reminders and paid notices are disabled, which is non-obvious behavioral context an agent could not infer from the annotation.

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 the critical 'WRITE' and no-draft warning, then organized into behavior, customer, items, and defaults. Dense with parenthetical cross-references but virtually no waste; slightly heavy for a single description block.

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 25-parameter mutation tool with no output schema, the description covers consequences, prerequisites, and sibling dependencies thoroughly. The one residual gap is that it never says what is returned (e.g., the new document id), which matters more given there is no output schema, but the behavioral coverage is otherwise strong.

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 100%, so the baseline is 3, but the description adds integrative meaning the schema does not: the either/or choice between id_customer and the customer_* fields, the minimum viable item shape (text + unit_price), and the net-vs-gross rule tied to calculate_vat. It does not explain every field, but the added cross-field guidance is real value.

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 ('Creates a document in Vyfakturuj') and clearly distinguishes itself from read-side siblings like vyfakturuj_get_invoice and vyfakturuj_list_invoices by starting with 'WRITE.' The title and description together make the operation unmistakable.

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?

Explicitly routes the agent to sibling lookups ('id_customer ... from vyfakturuj_list_contacts', 'id_number_series / id_payment_method come from vyfakturuj_list_number_series / vyfakturuj_list_payment_methods') and states when defaults apply otherwise. It also fences off adjacent concerns by stating what the tool does NOT do (no e-mail, no payment marking, no money movement).

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