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

Far exceeds the annotations. Annotations only say it is a non-read-only, open-world, non-destructive call; the description explains that cancellation is implemented as a new storno document with the same delivery date, that it is a legal filing to NAV, that it fails if the original was not accepted, and that it requires the Cotlet API key with app access. This is exactly the extra context annotations cannot carry.

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 core action and mechanism, and most sentences earn their place. Minor redundancy between the two confirmation-related sentences ('confirm each call' and 'confirm with the user before each call'), but nothing is padded.

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?

There is no output schema, and the description compensates by stating the return content (storno invoice number and amounts). Preconditions, auth requirement, and the irreversible-legal nature are all covered, so an agent has everything needed to call correctly.

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 invoice_number and reason are already documented in the schema (including that reason is printed on the storno). The description adds no syntax or format detail beyond that, so 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 (cancel), resource (an issued invoice), and the exact mechanism (creating a storno invoice with a reason). This distinguishes it not just from read siblings like list_invoices/get_invoice, but also from the naive expectation of deletion, so an agent knows it is a reversal-by-new-document operation.

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?

Provides a clear when-not ('A storno made by mistake is fixed in the app, not by this tool') and a precondition (NAV accepts only if the original was submitted successfully). It does not name a sibling alternative explicitly, so it stops short of a 5, but the selection context is clear.

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