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

Beyond the annotations, the description discloses the side effect (reminder recorded on the invoice, reminder count incremented up to a cap of 3), confirms nothing is sent to the customer and the PDF is delivered via a link, and explains that Fortnox itself is not touched until the person approves the prepared change. That is exactly the mutation-safety context the readOnlyHint=false annotation alone does not convey.

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?

The key facts — purpose, effect, trigger, no-send guarantee, approval flow, endpoint — are front-loaded in a compact block. There is mild redundancy: the no-send idea is stated twice ('Nothing is sent to the customer' and 'sends nothing to Fortnox'), which slightly blurs the distinction between customer delivery and Fortnox write-back.

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 one-parameter, approval-gated mutation with an output schema present, the definition covers everything an agent needs: the trigger, the effect and its cap, the fact that the customer receives nothing, and the two-stage approve-then-send model. Return values need not be described because an output schema exists.

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?

There is a single parameter, DocumentNumber, and schema description coverage is 100%, so the schema already carries the semantics. The description does not add format examples or constraints (e.g., whether it is a Fortnox document number vs. an internal ID or OCR reference), so the baseline of 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?

The opening clause names a specific verb and resource — 'Prepares a payment reminder for a customer invoice' — and immediately adds the concrete effect (PDF produced, recorded on the invoice, reminder count raised up to 3). No sibling in the catalog deals with reminders, so an agent can distinguish this from the many 'propose_*' invoice tools without inspecting the 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?

It gives a clear triggering condition: 'Use when the person asks for a reminder on an unpaid invoice,' which also encodes the precondition that the invoice must be unpaid. What is missing is explicit when-not guidance (e.g., what to do if the invoice is already paid or the count is already at 3), leaving edge-case routing to inference.

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