Drift evaluation report

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

Annotations declare readOnlyHint=true, and the description reinforces this by describing data aggregation without mutation. It adds behavioral context: lists worst-first flagged tickets with gaps, pending unscored tickets, and the Wilson interval for sampling. Contradictions: none.

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 concise (three sentences), front-loaded with purpose, and includes all essential information without redundancy. Every sentence adds value.

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 two parameters and no output schema, the description adequately explains what the tool returns (scores, intervals, flagged/pending tickets). It is complete enough for an agent to understand the tool's output, though it omits details like output format (e.g., JSON structure).

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 description adds that runId defaults to the latest run, which matches the schema's description. However, it does not provide additional meaning for the required 'project' parameter beyond its name. Schema coverage is 50%, and the description compensates somewhat by explaining the report's scope but not the parameters' formats or constraints.

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 uses specific verbs ('Aggregate') and lists concrete outputs (per-ticket scores, mean fidelity, verdict counts, drift rate, Wilson confidence interval, flagged tickets). It clearly distinguishes from sibling drift tools (drift_start, drift_record, drift_remediate) by focusing on aggregation and reporting.

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 after a drift run ('Aggregate a drift run') but does not explicitly state when to use versus alternatives (e.g., drift_record for raw records). No exclusion criteria or when-not-to-use guidance is provided.

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