propose_alert_rules

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

Describes zero side effects, data source (call patterns over lookbackDays), and output structure. No annotations, so description carries burden; it covers key behavioral traits adequately.

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?

Relatively concise for the information provided. Front-loaded with main action and distinction from create_alert. Each sentence adds value, though could be slightly trimmed without losing meaning.

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?

Given no output schema, description fully explains the return object including fields like baseline, proposals, skipped. Parameter is fully described. No missing context for an agent to use the tool correctly.

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?

Single parameter with 100% schema coverage. Description adds range, default, and context: 'analyze the call patterns over the past lookbackDays (7-30, default 14).' Also explains how lookbackDays appears in output.

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?

Clearly states it analyzes call patterns and proposes alert rules for cost/latency/error_rate/anomaly. Distinguishes from sibling tools like create_alert and list_alerts by emphasizing the propose-only nature.

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?

Explicitly separates proposal from creation: 'Applying them is a separate step via create_alert after customer confirmation.' Also notes that only non-overlapping rules are proposed, referencing list_alerts.

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