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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), while the description adds genuinely new behavior: the mutation books income into the accounts, is not sent to the customer, returns invoice number and totals, requires a Cotlet API key with app access, and requires per-call user confirmation. The 'reaches other people: confirm with the user before each call' disclosure is high-value context not derivable from the structured fields.

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 created/not-sent distinction, and every sentence carries information. There is mild redundancy between 'Issue an invoice and book the income' and 'Creates the invoice ... and registers the income in the accounts,' and the confirmation requirement is stated twice in slightly different words.

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 no-output-schema mutation with full schema coverage and present annotations, the description closes the remaining gaps: what is created vs. sent, what is returned, the lack of deletion, the correction workflow, auth requirements, and the confirmation obligation. Nothing an agent needs to invoke this 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 coverage is 100%, so the baseline is 3. The description goes modestly beyond it by stating the either/or shape of the input surface (draft_id vs. customer_id/days_until_due/lines) in one place, which helps an agent plan a call without cross-reading eight property descriptions. It adds no field-level detail (VAT types, currency defaults, date formats) beyond 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?

States a specific verb and resource ('Issue an invoice and book the income') and immediately disambiguates the closest siblings: 'It is created, not sent' and 'the customer gets nothing until send_invoice runs.' The dual creation path (from lines or from a draft_id) is also named, so an agent can separate this from create_invoice_draft and send_invoice without opening a 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?

Explicit routing: 'Pass draft_id to issue a draft, or customer_id, days_until_due and lines to create one directly,' naming the alternative path conditions. It also states the absence of a delete path and the substitute ('a wrong invoice is corrected with a credit note in Fiken'), which is exactly the when-not guidance an agent needs.

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