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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context, which it does: the result is computed server-side from live Fortnox data and spans all pages, telling the agent there is no pagination handling to do. It stops short of describing result shape or latency, but with an output schema present that is a minor gap.

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?

Three short sentences, front-loaded with the definition, then a concrete example question, then the computation note. No filler and nothing repeated from the schema.

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?

With an output schema present, return values need no explanation, and the two optional params are fully documented in the schema. The description supplies scope, data freshness and pagination behavior, making it callable without further guessing; only explicit sibling routing 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 description coverage is 100%, with both optional parameters ('namn' filename substring and 'mappar' comma-separated folder list with defaults) documented in the schema itself. The description adds no meaning about how filtering interacts with the 'unprocessed' scope, so baseline 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 description names a concrete resource and a precise filter: receipts, supplier invoices and documents sitting in the Fortnox inbox that have not been booked or linked. That 'unprocessed' qualifier is what separates it conceptually from the sibling get_inbox / list_inboxes, though it never names those siblings explicitly.

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 example question ("Ligger det kvitton i inkorgen som inte är bokförda?") implies the usage context without stating it as guidance. There is no explicit when-to-use vs when-not, and no pointer to get_inbox for the full inbox or to prepare_inbox_receipts for the follow-up action, so the agent must infer routing.

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