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

Goes well past the annotations: gapless sequential numbering (CN-0001...), PDF/page generation, default emailing to the customer, the effect on the outstanding balance, the refund side effect recorded on the invoice, books reversal of sale and tax, and a stated price ($0.10 per call, free on failure). These are exactly the consequences an agent must know before spending money on a mutation.

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 action and its three modes, then progressively adds side effects, the EU/voiding context, books impact, and price. Every sentence carries new information and there is no restatement of the title or schema.

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 money-moving mutation with 11 params and no output schema, the description covers what gets created (numbered credit note, PDF, page, email), what changes on the invoice and in the books, and the failure billing behavior. Nothing material is left for the agent to guess.

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 baseline is 3; the description still adds genuine meaning by explaining the mutual exclusivity/default of `lines` and `amount` ('Leave out lines and amount to credit the whole invoice') and the interaction of refunded with method/reference. It doesn't touch less obvious params like link_hours or to, but those are already well documented in the schema.

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?

Opens with a specific verb+resource ('Issue a credit note against a sent invoice') and immediately enumerates the three scopes (whole, lines, amount). The clause 'a sent invoice is corrected this way, not voided' implicitly separates it from invoices_void, so an agent can distinguish the siblings without opening schemas.

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 a real decision rule ('In much of the EU a sent invoice is corrected this way, not voided') and explains the refunded vs. credit distinction, which is the main branch point between two modes. It never names invoices_void, invoices_use_credit, or invoices_list_credits explicitly, so routing between tools is implied rather than stated.

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