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

The description adds meaningful behavior beyond the annotations: it states that the call 'links evidence only' and 'NEVER creates or changes a booking', and that already-matched documents are refused so attachments are never silently re-pointed. This complements the idempotent and non-destructive hints without contradicting them.

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 sentences with no filler. The action and scope are front-loaded, and every sentence adds a constraint, source reference, or safety clarification needed for correct invocation.

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 and annotations covering idempotence and destructiveness, the description covers all call-relevant context: purpose, source of event IDs, refusal behavior, org-scoped defaults, and the guarantee that no booking mutation occurs. Nothing essential 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 coverage is 100%, so the baseline is 3. The description adds extra value by explaining that event_id is a classified event id, e.g. from list_documents proposal.candidate_ids or get_unreviewed_events, and by clarifying that actor_id defaults to the organisation entity. This goes beyond the schema property descriptions.

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 opens with a specific verb and resource: 'Attaches a stored document ... to a bank transaction as its evidence'. It also names the two triggering scenarios (confirming a match_ambiguous proposal or resolving awaiting_transaction/extraction_failed documents), which clearly differentiates it from siblings like list_documents or approve_classification.

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?

Usage conditions are explicit: it should be used to confirm a match_ambiguous proposal with one of its candidate_ids or to manually resolve an awaiting_transaction/extraction_failed document. It also gives a clear when-not-to-use signal: already-matched documents are refused and it never creates or changes a booking, and it names source tools for event_id.

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