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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower; the description still adds that results are advisory and explains the response content ('each with the payments that fit it and why'). It does not mention whether candidates are ranked or how many are returned.

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 tight sentences with the core concept front-loaded and the important 'suggestions only' qualifier placed last for emphasis. The phrase 'money already recorded here' is slightly cryptic for a first-time reader but wastes no space.

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?

For a one-optional-parameter read tool with no output schema, the description adequately conveys what comes back and that nothing is committed. The main omission is the natural next step (confirming a suggestion via rec_match), which an agent would have to infer.

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% and the single optional 'account' parameter is documented in the schema as 'One account; all bank accounts when left out.' The description adds nothing about scoping, so the baseline of 3 applies.

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 the resource precisely — statement rows that might already be recorded money — and states the return shape (each candidate row with the payments that fit it and the reasoning). It is distinguishable from action siblings like rec_match or rec_unmatch, though it never explicitly contrasts itself with rec_matches or rec_get_match.

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?

'Suggestions only' implies this is the advisory step before a committing action, but it never names rec_match as the follow-up or states when to prefer this over rec_matches. Usage is inferable rather than instructed.

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