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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds crucial behavioral context: no undo, immediate persistence across all candidate entries, no single-record targeting, ephemeral entries linked to canonical transactions, and deterministic escalation. This goes well beyond what the annotations convey.

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?

The description is front-loaded with the most critical warnings (destructive, business-wide, no undo) and remains focused on actionable distinctions. However, it repeats the 'WHOLE' scope and 'NO undo' warnings, which adds slight redundancy even if intentional for emphasis.

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?

Given zero parameters, no output schema, and a highly destructive operation, the description covers scope, behavior, side effects, alternatives, and reversibility. Nothing an agent needs to decide whether and how to call this tool 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?

The tool takes zero parameters, so there is no parameter semantics for the description to add or compensate for. Baseline for zero parameters is 4; the empty schema is sufficient.

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?

States a specific verb and resource ('Reconciles the WHOLE business's books'), details the three operations (dedupe, categorise, link), and explicitly distinguishes itself from the single-record alternative find_candidate_transactions. An agent can immediately tell what this tool does and does not do.

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?

Gives explicit when-to-use ('reconcile the WHOLE business'), when-not-to-use ('never for one record'), and names the alternative ('use find_candidate_transactions instead' for one invoice or bill). No inference required.

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