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 real behavioral context: the record is a draft with no invoice number, no confirmation prompt is triggered, the discount applies to the whole invoice, the response contains SnelStart-calculated totals, and a Cotlet API key with app access is required. That is substantive information the annotations do not 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?

Purpose and the no-send guarantee are front-loaded in the first sentence, and the Dutch UI label mapping is genuinely useful for disambiguation. A few clauses (no invoice number / nobody receives it / no confirmation) overlap in meaning, but the text is short and earns most of its space.

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 write tool with no output schema, the description covers state semantics, confirmation behavior, auth requirements, and even what the response returns (calculated totals). It does not mention error cases or how the saved concept is later issued, which is a minor gap given the annotations already establish the mutation profile.

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 every parameter is already documented, including discount scope and vat_mode values. The description's 'Discounts apply to the whole invoice' merely restates the discount_percent schema text and adds no syntax or format detail beyond it.

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 (saves a sales invoice as a concept, without sending it) and pins down the exact semantic difference from an issued invoice: no invoice number, nobody receives it. An agent can distinguish this from snelstart_issue_sales_invoice or snelstart_create_credit_invoice without inspecting any 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?

The description clearly frames the usage context: this is the 'Tussentijds opslaan' path that keeps a draft in the invoice overview, versus a send/issue action. However, it never names the alternative tool (e.g. issue_sales_invoice) or states an explicit when-not condition, leaving the agent to infer the contrast.

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