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

Annotations only cover readOnlyHint=false/openWorldHint=true/destructiveHint=false, but the description adds real operational context: it returns Exact-computed ID/number/total, does not send, is confirmation-gated by default with an opt-out, reaches other people requiring user confirmation, and needs a Cotlet API key with app access. No contradiction with annotations.

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 purpose and the non-sending constraint, then expands into return values and auth. The non-sending point is stated twice ('It does not send it' and 'It does not send the invoice'), a minor redundancy, but every sentence otherwise earns its place.

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?

Covers the full call context for a mutation tool: return shape (invoice ID/number/total despite no output schema), confirmation default and opt-out, package availability, auth requirement, and the alternate send step. Nothing an agent needs to invoke 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 both the required and optional parameters (customer, invoice_date, lines, division, your_ref) are already documented in the schema. The description only reinforces that lines belong with the header and adds no new syntax or format detail, 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 (Create), resource (sales invoice with its lines for a customer), and the atomicity guarantee that lines ship with the header. It also names the sibling it is distinct from (send_sales_invoice), so an agent can route 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?

Explicitly says the tool does not send the invoice and that send_sales_invoice is the alternative, and notes the endpoint exists only in some Exact packages, giving a precondition. Both when-to-use and the alternative path are stated, not inferred.

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