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

Adds substantial context beyond the annotations: the draft gets no invoice number, reaches no one, can be edited or deleted later, and therefore runs without a confirmation prompt. It also discloses the auth requirement (Cotlet API key with app access). This is exactly the behavioral detail a mutation tool needs.

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?

Purpose is front-loaded and the safety/auth notes follow logically. Minor redundancy: 'without a number' is stated twice, and the 'Zapisz szkic' gloss is nice but slightly padded. Overall efficient.

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 non-destructive draft-creation mutation with no output schema, the description covers what matters: what is created, its scope (internal, unreviewed), reversibility, no confirmation, and auth needs. Nothing needed to call it correctly is missing.

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%, so the schema already documents lines, dates, contractor_id, and calculate_from. The description only adds a cross-reference ('same parameters as issue_invoice'), which is marginal value over the schema. Baseline 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?

States a specific verb+resource (save an invoice as a draft) and immediately qualifies the key distinction: it is saved *without a number*, unlike a real issued invoice. It names the sibling issue_invoice by relating the parameter set, so an agent can tell the two apart without opening either schema.

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 clear context for use ('to review and issue in the app') and contrasts with issue_invoice by referencing the shared parameters. It does not give an explicit 'use this instead of issue_invoice when X' rule, but the purpose-plus-alternative framing makes the choice clear.

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