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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: results are computed server-side from live Fortnox data and aggregated across all pages, which tells the agent about freshness and pagination.

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 extracted fields are front-loaded in the first clause and the example question is a compact, purposeful illustration of intent. The trailing note about server computation and pagination is slightly boilerplate but still earns its place.

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?

An output schema exists, so return-value detail is not required, and the description identifies the input source (inbox/archive file id) and the extracted fields. What is missing is only error/edge behavior, e.g. what happens if OCR cannot be found in the document.

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%, and the single 'id' parameter is documented as the file id in inbox or archive with a required note. The description's phrase 'ur en fil i inkorgen eller arkivet' echoes but does not extend the schema, so the baseline of 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 (interpret an invoice) and enumerates what is extracted: amount, date, OCR, organisation number, supplier, from a file in inbox or archive. This is clearly distinct from get_supplier_invoice or list_supplier_invoices, though it does not explicitly contrast itself with read_inbox_file/read_archive_file/read_documents, which read the same storage locations.

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 ('Läs leverantörsfakturan som ligger i inkorgen och ta fram belopp, förfallodag och OCR') conveys the intended usage context, but there is no explicit when-to-use/when-not guidance and no named alternative such as read_inbox_file or get_fortnox_document for agents that only need the raw file.

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