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

Beyond the annotations (idempotentHint, destructiveHint), the description discloses that it 'writes user overrides that AI enrichment never overwrites' and 're-derives each bookkeeping journal entry.' It also warns about the scope ('booking every match') and advises previewing the impact. This adds valuable behavioral context about persistence and side 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?

The description is three sentences, front-loaded with the primary purpose. It includes essential behavioral details and a clear directive to preview. There is no fluff or repetition; every sentence contributes value.

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 that an output schema exists, the description doesn't need to explain return values. It covers the action, side effects, and a crucial prerequisite (previewing). It could mention that a rule ID is required and that the operation affects many rows, but the preview instruction covers that. Overall, it is sufficiently complete for a bulk operation tool.

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 100% coverage with generic descriptions ('UUID value wrapper'), so the description doesn't add much beyond that. It does give context that ruleId refers to an existing rule and companyId to a company, but these are already implied. The description does not explain the nested structure or provide additional semantic meaning beyond the schema.

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 states a clear action: 'Apply an existing categorization rule to the company's transaction history, booking every match to the rule's account.' It specifies the resource (transaction history), the operation (apply rule), and the effect (booking matches). It distinguishes itself from related tools by referencing the preview tool and describing a bulk, rule-driven operation.

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 explicitly instructs to preview first with transaction_preview_categorization_rule, which is a direct usage guideline. It implies the tool is for applying an existing rule broadly rather than categorizing a single transaction, though it doesn't explicitly contrast with transaction_categorize_transaction or batch tools. The guidance to preview is clear and actionable.

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