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

The description adds 'writes nothing', which reinforces the readOnlyHint true annotation. It also discloses the return content: 'ranked taxonomy option codes with confidence and a short rationale,' providing useful behavioral context beyond the annotations. No contradiction with annotations.

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 two sentences with no filler. The first sentence leads with the primary purpose, and the second adds key differentiators (return type and non-mutating behavior). Every phrase 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?

For a simple read-only tool with two required parameters and an existing output schema, the description is complete. It states what the tool does, what it returns, that it writes nothing, and how to apply the result. No additional context is needed for an agent to use it correctly.

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 already provides descriptions for both parameters (100% coverage) as 'UUID value wrapper.' The tool description does not add parameter-specific meaning, so it does not exceed the schema baseline. The description's reference to 'a transaction' is generic and not tied to the parameters.

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 clearly states the action ('Recommend a bookkeeping category for a transaction') and the mechanism ('using the platform classifier agent'). It also distinguishes itself from the sibling tool transaction_categorize_transaction by noting it 'writes nothing' and explicitly points to that tool for applying.

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 provides an explicit alternative: 'Apply one with CategorizeTransaction.' This makes the intended use clear—this tool generates suggestions, while the sibling applies them. It also implies when to use it (when a recommendation is needed) and distinguishes it from the write operation.

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