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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the primary behavioral aspects. The description adds modest context by describing the aggregation behavior and the time filter, but does not mention any side effects, error conditions, or rate limits beyond what the annotations imply.

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 a single sentence that states the primary action and key qualifiers without any extraneous text. It front-loads the main intent ('Aggregate evaluation counts and flag distribution') and is appropriately concise.

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 lack of an output schema, the description does not explain the return structure, which could be a gap. However, it does convey the core purpose and the important parameters, and for a read-only aggregation tool, the information provided is likely sufficient for an agent to call it correctly. Omission of return details is the main shortfall.

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 100%, so the schema already explains each parameter. The description adds little beyond the schema: it mentions 'since the given timestamp' but that is already in the 'since' parameter description. No additional parameter details are provided that are not already present.

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 states a specific verb ('Aggregate') and a clear resource ('evaluation counts and flag distribution for an Assignment's Jobs since the given timestamp'). It clearly differentiates from sibling getters like getEvalRubrics or listRuns by specifying an aggregation over evaluated jobs with a time filter.

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 usage context by mentioning the timestamp filter and the aggregation nature, which suggests it is for summary metrics rather than individual records. It also hints at the 'scope' parameter's effect indirectly via the description of revision_id, but it does not explicitly state when to prefer this over alternatives.

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