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

Annotations already declare this as a safe, read-only, idempotent operation, so the bar is lower. The description adds useful behavioral context by defining what counts as a run and clarifying that filtering is based on when runs ended, plus the aggregate metrics returned.

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 definition is a single dense sentence with no filler. It is appropriately concise, though it front-loads the definition of a run rather than the action and could be structured more clearly for scanning.

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?

An output schema exists, so return-value details need not be in the description, and annotations cover the safety profile. However, with five parameters and low schema description coverage, the description is incomplete regarding filter parameters and the limit behavior.

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 description coverage is only 40%, and the description only hints at the date-range parameters. It does not explain the feature, customer, or limit parameters, nor does it compensate for the undocumented schema fields.

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 the resource (agent runs/conversations/jobs identified by run id or OpenTelemetry trace) and the returned metrics (count, total, average, median, p90, most expensive). It is specific but does not distinguish this aggregate tool from sibling tools such as get_run, get_spend, or get_customer_cost.

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 implies the tool is for runs ending in a date range, but it gives no explicit when-to-use guidance, no when-not-to-use guidance, and no alternatives among the many sibling cost tools. An agent must infer the appropriate context.

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