Call Metrics

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

Annotations already declare readOnlyHint=true, consistent with description. Description adds detail on returned metrics (success rates, latency, top errors, breakdown) but does not disclose rate limits, data freshness, or other behavioral traits. Acceptable given annotation coverage.

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?

Extremely concise single sentence with front-loaded verb and resource. No wasted words, efficiently conveys purpose.

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?

Adequately covers purpose and output for a simple read-only tool. Lists specific metric categories and breakdown dimensions. No output schema requires explanation of return structure, which is sufficiently hinted. Slight gap: no mention of whether data is historical or real-time.

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 fully describes the sole parameter (windowMinutes) with type, default, and description. Tool description adds no additional parameter semantics. Baseline 3 at 100% schema coverage.

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 uses specific verb 'Get' and resource 'observability metrics', listing concrete metric types (success rates, latency, top errors, breakdown by tool and target). Clearly distinguishes from siblings like recent_errors (specific errors) and circuit_status (circuit breaker state).

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?

No explicit guidance on when to use this tool versus siblings. Description only states what it does, leaving the agent to infer when to prefer it over recent_errors or circuit_status.

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