Resolve Matched Transactions

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

Goes well beyond the annotations by disclosing dedup of up to 50 IDs, that 'orphan' is returned only for a 404 transaction, that 'found' includes a row for duplicate review but is not proof to delete it, and that other failures abort with an error. The 'Read-only' statement is consistent with readOnlyHint=true rather than contradicting it.

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?

Compact and front-loaded with the action, and every clause carries behavioral weight. The density of unexplained jargon makes it harder to parse than ideal, but there is no filler.

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 edge cases are well covered and an output schema exists, so return values needn't be spelled out. However, with 0% schema coverage the unexplained budgetId is a real gap for an agent trying to call it correctly.

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%, so the description carries the full burden, yet it leaves budgetId entirely unexplained and only loosely references matchedTransactionIds. The '50 IDs' dedup limit is already encoded in the schema's maxItems, so it adds little parameter meaning.

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 specific internal concepts (match_broken matched_transaction_id values, review_unapproved) and a resource, but the verb 'resolve' is vague and the jargon is opaque to an agent that doesn't already know these domain terms. It hints at a relationship to review_unapproved but doesn't clearly distinguish itself from that sibling.

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?

Naming review_unapproved as the source of the IDs implies the workflow (call review_unapproved first), but there is no explicit when-to-use vs when-not or alternative-tool routing. Usage must be inferred.

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