expenses_review_queue

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

There are no annotations to rely on, so the description carries the full burden. It does not state whether this is a read-only operation, whether it requires any authentication, or what side effects (if any) exist. The phrasing 'inbound payments the matcher would not auto-match' implies a read/list operation, but this is not explicit. The description provides no behavioral details beyond the content, leaving the agent to guess about safety and effects.

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?

Two sentences with zero waste. The first sentence states the tool's purpose and sorting, the second gives the immediate next action. All key information is front-loaded and no redundant details are present.

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?

The tool is simple (one optional parameter, no output schema), and the description provides the essential context: what the queue contains, how it's ordered, and what to do with the items. It does not describe the output structure, but that may be implied as a list of payments. Missing explicit read-only status is a minor gap but not critical for usage in a review context. Overall, the description covers the core needs despite omitting parameter details.

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?

The schema has a single parameter 'limit' with 0% description coverage and no description in the tool description. The description says nothing about 'limit'—its meaning, default, allowed values, or behavior. While 'limit' is a common term for pagination or result size, the tool description does not clarify it, and with no schema description the agent must infer. This is a gap given the description had room to explain it.

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 is specific: it identifies the tool as a queue of inbound payments that the matcher did not auto-match, sorted by best candidate. This clearly distinguishes it from the sibling expenses_resolve (the action tool) and other expense tools. The verb 'review' is implicit in 'queue' and the context is unambiguous.

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?

It explicitly states that these payments need a decision via expenses_resolve, telling the agent the intended follow-up action. This differentiates the tool from others and gives clear 'when to use' context. However, it does not explicitly discuss when NOT to use it (e.g., auto-matched payments are handled elsewhere), nor does it weigh alternatives like reconcile or expenses_spend. Still, the guidance is strong enough for a clear call.

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