detect_customer_churn

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

With no annotations, the description discloses the core classification logic: how average order interval and churnThreshold produce medium/high risk labels. It does not, however, disclose the output form (e.g., returns flagged customer list?) or any data prerequisites/side effects. Since the tool is clearly analytical, the missing output semantics are the main transparency gap.

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?

Three sentences with no waste: purpose, mechanism, application. The most decision-relevant information (purpose + logic) comes first. Front-loaded and appropriately sized.

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 read-only analytic tool with two fully documented optional parameters and no output schema, the description is close to sufficient but stops short: it never states what the tool returns (e.g., a list of at-risk customers, risk levels). It also lacks any note on prerequisites such as requiring order-history data. Still minimum viable for safe invocation.

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 describes both parameters (lookbackDays: 'History window for purchase pattern learning'; churnThreshold: 'Days of silence = high churn risk'), so baseline is 3. The description adds that churnThreshold gates high risk and lookbackDays bounds interval computation, but not much beyond the scheaa.

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?

Opens with a direct verb-resource statement: 'Predict customer churn risk.' It then specifies the exact mechanism (average order interval, overdue→medium, ≥churnThreshold→high), distinguishing it from siblings like calc_customer_clv and segment_customers_rfm. This is specific enough for an agent to know what it does and how.

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?

States a concrete use context: 'Helps target re-engagement campaigns.' It does not name any alternatives or specify when not to use it, so the agent must infer selection from the purpose rather than explicit routing. The context is clear, but there are no exclusions/alternatives.

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