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

Adds substantial context the annotations cannot convey: despite write-flavored hints (readOnlyHint=false), the description makes clear this is a proposal-only tool that sends NOTHING to Fortnox and whose response explains how the approved change is dispatched. It also discloses that no money moves and that idempotency stems from bookkeeping an already-registered payment.

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-loads the action, then the endpoint, then the critical scoping and no-side-effects notes. It is dense but every sentence carries information; the inline API URL is the only borderline redundancy given the endpoint is already named.

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 two-parameter proposal tool with an output schema, the description covers what it does, what it does not do, which identifier to pass, the request body shape, and where the result goes. 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 coverage is 100%, but the description still adds real meaning: Number is the payment's own identifier, not the invoice number — a distinction the bare schema ('identifies the invoice payment') does not make. It also supplies the expected body envelope, {"InvoicePayment": {…}}, which the schema only hints at with a loose anyOf.

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 ('Bookkeep an invoice payment') and pins it to the Fortnox PUT /3/invoicepayments/{Number}/bookkeep endpoint. It then explicitly distinguishes itself from payment creation ('does not create or register a payment'), separating it from propose_create_invoice_payment in the sibling list.

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 clear preconditions: the payment must already be registered in Fortnox, and this tool only prepares a change for human approval while sending nothing itself. The alternative (creating a payment) is described by negation rather than named, so the agent must map 'does not create' to propose_create_invoice_payment itself.

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