Start a drift evaluation

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

Describes the return value (runId + tickets to score) and the two modes. Annotations are all false, providing no safety signals; the description compensates by explaining it initiates a run. Could be more explicit about side effects, but sufficient for a start action.

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 purpose and mode explanation. The embedded workflow adds length but is highly valuable. Every sentence contributes to understanding usage. Could be slightly more concise by separating workflow into a separate note.

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 no output schema, the description provides necessary return info and a complete post-invocation workflow. It fits well within the sibling tool list and gives enough context for an agent to use it correctly without additional documentation.

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?

With only 40% schema coverage, the description adds significant meaning: clarifies that 'sample' mode uses a seeded random subset, seed is auto-generated if omitted, and sampleSize only applies to 'sample'. However, it does not describe the 'project' or 'type' parameters beyond what the schema provides.

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 tool starts a drift evaluation over Done tickets, distinguishing between 'sample' and 'full' modes. It differentiates from sibling tools like drift_record and drift_report by being the first step in a documented workflow.

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?

Explicitly explains when to use 'sample' vs 'full' based on need for speed vs completeness. Provides a complete workflow after invocation: use get_work_packet, drift_record, then drift_report. Also suggests using the evaluate_drift prompt for the full loop.

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