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

Annotations only say readOnlyHint=false and idempotentHint=true; the description adds the crucial behavioral fact that the tool sends NOTHING to Fortnox and merely stages a change for human approval, plus that the response explains how the approved change is dispatched. That is exactly the kind of context annotations cannot convey. It does not mention required scopes or what happens on re-proposal of an already-bookkept invoice, so not a 5.

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?

Four short clauses, front-loaded with the action, then the endpoint reference, then the critical no-send caveat. The API URL is redundant with the endpoint path already cited but is minor waste. No filler prose.

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 propose tool with an output schema and full schema coverage, the description covers the essential unknowns: it is non-mutating externally, awaits human approval, and the response describes the dispatch mechanism. Missing only error/precondition behavior (e.g. invoice already bookkept), which is a modest gap rather than a blocking one.

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 both parameters are already documented ("identifies the invoice", "The request body, as Fortnox expects it: an object"). The description's {"Invoice": {…}} wrapper hint adds a small amount of value about body structure beyond the schema's generic object type, but nothing about DocumentNumber format or where to obtain it. Baseline 3 is appropriate.

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+resource ("Bookkeep an invoice") and pins it down with the exact Fortnox endpoint PUT /3/invoices/{DocumentNumber}/bookkeep, so the resource path (customer invoice, not supplier invoice) is unambiguous. It doesn't explicitly name sibling tools like propose_bookkeep_supplier_invoice or propose_bookkeep_invoice_payment to differentiate, so it stops short of 5.

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 implies usage through the workflow note ("Only prepares the change for the person to approve"), which tells an agent this belongs in the propose-then-approve flow. But it never states when to choose this over propose_bookkeep_invoice_payment or propose_bookkeep_supplier_invoice, nor any preconditions such as the invoice needing to exist or be unbooked.

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