evaluations_by_metric

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

The description adds significant behavioral detail beyond the annotations, including the exact output format (flat series without datasets or uniqueTotal), the per-app addons structure, and the behavior of ignored parameters. It also references the API spec for further clarity, fully informing the agent of what to expect.

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?

The description is compact but packs essential details: purpose, output shape, filter limitations, and a link to the API spec. It is front-loaded with the main purpose. While slightly dense, every sentence adds value with no wasted words.

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 the tool has 4 parameters, complete schema coverage, and no output schema, the description compensates by explaining the output structure in detail. All parameter behaviors are covered, and the context of ignored filters is provided. No gaps remain for the agent's effective use.

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 coverage is 100%, so the description does not need to repeat schema definitions. However, it adds value by listing allowable metric values with error conditions, stating the default for aggregation, and clarifying which parameters are ignored. This contributes to understanding beyond the schema.

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?

The description clearly states 'Evaluation time-series grouped by a dimension' and explains the output structure (FLAT total.series[], per-app addons). It specifies the grouping dimensions from the metric parameter and notes which filters are ignored, making the tool's purpose unambiguous and distinguishing it from other evaluation tools.

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?

The description provides context on usage by listing the only effective filters (aggregation, startDate, endDate) and noting that productId/hosting/addon are silently ignored. However, it does not explicitly mention when not to use this tool or suggest alternative tools among siblings, so it lacks exclusion guidance.

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