Start a drift evaluation

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

The description explains the behavior of the two modes ('sample' as fast statistical estimate, 'full' as exhaustive) and notes that it returns a runId and tickets to score. Annotations are neutral (non-readOnly, non-idempotent), and the description adds value beyond them by detailing the mode behavior and return data.

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 front-loaded with the core purpose, then expands on modes and usage. It is a single paragraph but contains essential information without excessive verbosity. It could be slightly more concise by omitting the post-step instructions, but they are helpful.

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's role in a multi-step workflow, the description provides a complete context: what it does, its modes, return values, and how it fits with sibling tools. No output schema exists, but the return is described. The reference to the evaluate_drift prompt further aids completeness.

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 clarifies the 'mode' parameter by explaining the two options and their implications, and implies 'sampleSize' for the sampling mode. However, other parameters like 'type' and 'project' are not elaborated, and schema coverage is only 40%. The description partially compensates but leaves gaps.

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 it begins a drift-evaluation run over a board's Done tickets, with specific modes ('sample' and 'full'). It uses the verb 'Begin' and resource 'drift-evaluation run', distinguishing it from sibling tools like drift_record and drift_report.

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 explicitly outlines when to use this tool (first step of drift evaluation) and provides a step-by-step workflow: after this, compare tickets using get_work_packet, call drift_record, then drift_report. It also suggests using the evaluate_drift prompt for the whole loop.

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