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

Annotations already cover the read-only/open-world/destructive profile, yet the description still adds sorting order, the presence of a document_url for reading the file, the lifecycle caveat that deleting a purchase leaves the inbox document intact, and the auth requirement (Cotlet API key with app access). That is substantial behavior disclosure beyond structured fields.

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?

Well front-loaded: identification, ordering, definition of 'used', item shape and auth are ordered sensibly and each sentence carries distinct information. The opening sentence slightly restates the title, and the deletion caveat is a minor tangent, so it is not flawless.

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?

There is no output schema, so the description correctly fills that gap by describing the item shape (name, upload date, used flag, document_url) and ordering, and the cursor param handles pagination. An agent has everything needed to call and interpret results.

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 the baseline is 3; however the description adds interpretation for the status enum ('filter by unused to get the receipts that still need booking') that the schema's terse 'all, unused or used' does not convey, lifting it above baseline.

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 ('Documents in the Fiken inbox'), names the concrete data fields returned, and defines scope ('Innboks, newest first'), which cleanly separates it from fiken_list_purchases and fiken_list_invoices without the agent needing to open a 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?

Gives real usage guidance: it explains what 'used' means and that filtering by unused surfaces receipts still needing booking, so the agent knows how to select this tool for a bookkeeping task. It stops short of naming alternatives or stating when NOT to use it, so it stays at 4.

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