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

Beyond the annotations (idempotentHint true, destructiveHint false), the description discloses significant side-effects: it applies to both the income/expense detail field and umbrella category, writes a permanent user override that AI enrichment never overwrites, and causes the journal entry to re-derive. This is rich, contextual behavioral disclosure.

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?

Four sentences, each adding unique value. The first states the core action, the second and third describe automatic side-effects, and the fourth provides code discovery guidance. No redundancy or filler.

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 and annotations present, the description sufficiently covers purpose, side-effects, and parameter sourcing. The only minor gap is that categoryOptionCode is optional in the schema while the description implies it is always needed for the operation.

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 67%: companyId and transactionId only have 'UUID value wrapper', while categoryOptionCode lacks a description. The description adds meaning by explaining categoryOptionCode is a taxonomy option code, giving examples, and directing to field tools for valid options. This compensates for the undocumented parameter.

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 opens with a specific verb+resource+method: 'Set a transaction's category by taxonomy option code'. Examples clarify the code format, and the final sentence directs to field tools for valid codes, distinguishing this tool from the sibling 'transaction_suggest_transaction_category' which suggests rather than sets.

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?

It instructs to find valid codes via field tools before using this tool, giving a clear prerequisite. It implies this is for manual categorization vs. suggestion, but does not explicitly name alternatives or state when not to use it.

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