Detect Anomalies

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

Annotations already mark the tool as read-only and idempotent. Description adds critical behavioral details: baseline comparison with self-exclusion, floor scaling when history is near-constant, and explains scale_basis/scale_multiple. No contradictions 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?

Two sentences, front-loaded with actionable purpose. Every sentence adds unique information with zero 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?

No output schema, but tool complexity is moderate. Description covers detection mechanics well, though missing details on return format (e.g., how anomalies are reported). Still sufficiently complete for agent decision-making.

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%, so baseline is 3. Description adds value by explaining the algorithmic context (floor scaling, sigma use) that enriches parameter meaning beyond schema descriptions, especially for sensitivity and history_months.

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?

Description explicitly states 'Find unusual transactions' and enumerates specific anomaly types (abnormal amounts, large charges from new payees, potential duplicates). Clearly distinguishes from sibling tools like search_transactions or detect_recurring_charges.

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?

Implied usage for detecting transaction anomalies but lacks explicit when-to-use or when-not-to-use guidance. No mention of alternatives or exclusions, leaving the agent to infer context from sibling list.

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