set_merchant_category

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It goes beyond the input schema by revealing the side effect: 'adds a rule and recategorizes that merchant's existing transactions.' It also discloses the special requirement for setting category='Random' (confirm_random=true) and discourages that action. This is meaningful behavioral context, though it omits details like reversibility or permission requirements, preventing a perfect score.

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 long, front-loading the primary action ('Pin a merchant...') before the caveat about Random. Every sentence adds value: the first states the core behavior and side effect, the second provides an important usage warning. There is no redundancy or filler, earning the highest score.

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 tool with 4 parameters, no annotations, and no output schema, the description covers the essential context: what it does, its side effect, and a critical edge case (Random category behavior). It does not explain return values or error conditions, but given the tool's straightforward nature, this is a minor gap. The description is more complete than the average 3, but lacks additional depth like conflict handling or undo options.

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 0%, so the description must compensate for the bare parameter list. It does so by explaining merchant_norm as a 'substring' and describing the role of category and optional subcategory. It also clarifies the confirm_random parameter's purpose in the context of the 'Random' category. While it doesn't detail allowed values or formats, it gives functional meaning to all 4 parameters, which is strong given the lack of schema documentation.

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 tool's function: 'Pin a merchant (merchant_norm substring) to a category (+ optional subcategory)' and explains that it 'adds a rule and recategorizes that merchant's existing transactions.' This specific verb-resource pairing distinguishes it from sibling tools like set_txn_category (which targets a single transaction) and add_custom_category (which creates a new category definition).

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 clear context for when to use the tool: to create a persistent merchant-to-category rule that affects existing transactions. It also gives usage guidance by warning against setting category='Random' and advising to 'pick a real category or leave it in the review queue,' implicitly steering users away from misuse. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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