Get Cost Summary

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds behavioral details about what the tool returns (total spend, call counts, error rates, etc.) and that revenue attribution is conditional. 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 that efficiently convey purpose and usage guidelines. No redundancy or unnecessary words. Front-loaded: the first sentence states the primary function.

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 high-level overview tool with one optional parameter and no output schema, the description sufficiently explains the return contents (spend, calls, errors, etc.) and provides context on when to use it. It covers all needed information for an agent to decide if this tool is appropriate.

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?

Input schema coverage is 100% and already describes the single parameter (period_days with default 30). The description does not add any additional semantic context for this parameter beyond what the schema provides, so a baseline of 3 is appropriate.

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 the tool returns a comprehensive cost summary for an AI agent fleet, listing specific data points (total spend, call counts, error rates, etc.). This distinguishes it from sibling tools like metrx_get_agent_detail or metrx_get_task_roi, which focus on narrower aspects.

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 says 'Use this as the starting point for understanding your agent economics' and warns against real-time per-request use, recommending OpenTelemetry spans instead. This provides clear when-to-use and when-not-to-use guidance, as well as an alternative.

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