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

Annotations are all false, so the description carries the behavioral burden. It discloses useful internal behavior: 'Amounts store negative, reusing the invoice's own rates,' which explains storage and VAT handling. It also surfaces the quota 'Free: 5 a month' and the companion workflow with credit_note_text. No annotation contradiction exists.

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?

The description is short and front-loaded. The first sentence immediately states the core action and modes, while each following clause adds distinct value: storage behavior, quota, and the follow-up with credit_note_text. No sentence is wasted.

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 creation tool with six parameters, no output schema, and no useful annotations, the description covers the key decision space: what modes exist, how amounts behave, quota limits, and the intended follow-up action. It does not describe return values or failure behavior, but the schema covers parameter needs and the description provides enough contextual guidance for correct invocation.

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 baseline is 3. The description adds value above the schema by summarizing how the parameters relate: the whole invoice, a GROSS amount_minor split across VAT rates, or named lines. This clarifies the mode-selection semantics beyond individual field descriptions.

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 opens with a specific verb and resource ('Credit one invoice') and then distinguishes the three supported modes: whole invoice, gross amount_minor split over VAT rates, or named lines. This clearly separates credit_note_create from siblings like credit_note_delete, credit_note_get, and credit_note_list.

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 description gives clear context for when to use this tool: to credit an invoice in one of three ways. It also provides actionable follow-up guidance by saying 'Send it with credit_note_text.' It does not explicitly state when not to use alternatives or mention exclusions, but the sibling roles are clear enough.

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