get_rule_candidates

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

Since no annotations are provided, the description carries the burden of showing behavior. It correctly implies a read-only, analytical nature by saying 'suggest new rules' and 'input for create_transaction_rule' (not the rule creation itself). It also discloses the return structure. It could add more detail on defaults or exclusions, but the schema covers some of that.

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 concise sentences: purpose, output fields, and usage hint. Every sentence carries functional value, with no wasted words.

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 4-parameter tool with no output schema and no annotations, the description adequately conveys purpose, output shape, and workflow. It could mention default exclusions or lookback behavior, but the schema handles that. The description is overall sufficient for an agent to select and invoke the 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?

Schema coverage is 100% with detailed descriptions for all four parameters, so the baseline is 3. The description adds thematic context ('recent transactions', 'consistent category pattern') that aligns with lookback_days, min_confidence, and min_transactions, but it does not add specific parameter 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 clearly states the tool analyzes recent transactions and suggests new rules for merchants with consistent category patterns. It specifies the output fields (merchant pattern, suggested category, confidence score, transaction count) and distinguishes itself from siblings like get_transaction_rules by focusing on rule candidates rather than existing rules.

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 a clear usage context by labeling the output as 'High-value input for create_transaction_rule', implying it is used before creating a rule. However, it does not explicitly mention alternative tools or when not to use it, such as comparisons with get_categorization_suggestions.

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