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

Annotations already establish that this is a safe read (readOnlyHint=true, destructiveHint=false), so the 'Writes nothing' line is largely redundant. However, the description adds genuinely useful behavioral detail beyond annotations: the matching algorithm (exact amount match, then date proximity and description ranking).

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?

Three tightly written sentences, front-loaded with the core action, followed by the matching logic and the safety note. No filler; every sentence earns its place.

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, return values needn't be explained. The description covers purpose, matching logic, and non-mutating behavior adequately for a 2-parameter read tool. Only the absence of explicit alternative-tool routing keeps it from a 5.

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 100% and both parameters (statementId, companyId) are documented in the schema. The description adds no parameter-level detail, so the baseline of 3 is appropriate.

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 gives a precise verb and resource: 'Rank ledger transactions against a statement's unmatched lines.' An agent immediately understands this is a candidate-scoring tool for reconciliation. It does not explicitly name a sibling (e.g., accounting_suggest_transfer_pairs), so it falls just short of the explicit-differentiation bar.

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?

The description sets the usage context clearly — matching against a statement's unmatched lines with a human applying the final match on the reconcile screen. It communicates the advisory nature of the tool but doesn't name alternatives or state explicit exclusions.

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