folio_attach_invoice

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

Adds real behavior beyond the annotations: the approval coupling, rejection of a modified event, the fact that no payment or explicit completion marking occurs, and non-idempotent retry advice that reinforces idempotentHint=false. The 'no payment / no explicit completion' note is exactly the kind of side-effect boundary an agent cannot infer from readOnlyHint/destructiveHint alone.

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?

Five short sentences, verb-first, each carrying distinct information — prerequisite, rejection rule, effect scope, retry warning. No filler or repetition.

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?

Behavioral and safety context is adequate, and without an output schema the description sensibly covers effects rather than returns. But for a mutation whose only input is a proposal_id, the absence of any explanation of that identifier or its relation to the Terminal approval leaves a meaningful invocation gap.

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 0% and the description never mentions proposal_id or how to obtain one; it instead talks about a 'selected Folio event', which does not map onto the parameter name. With one required, undocumented parameter the description should compensate and does not.

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 — attach/upload an approved invoice attachment to a chosen Folio event — which is distinguishable from sibling reads (folio_read_attachment) and preparers (folio_prepare_invoice_assignment, folio_match_invoice). It stops short of explicitly contrasting with those siblings, and 'valgt Folio-hendelse' sits oddly against the single proposal_id parameter.

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 concrete preconditions (requires an unused Terminal approval bound to the same file/event/profile) and an explicit when-not (do not retry when the outcome is unclear; a changed event is rejected). It never names an alternative tool to use instead, so it is strong on context but short of full routing guidance.

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