drift_latest

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

Annotations already establish readOnly/non-destructive/closed-world, and the description adds real behavioral context on top: the failure mode when scan history is insufficient, and that thresholds default to the CLI values 0.20/5.0. It stops short of describing the response shape or what the thresholds actually gate.

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?

Three dense sentences, front-loaded with purpose, then precondition, then defaults. The trailing '(D1-06)' is internal shorthand that costs a few tokens without informing the agent.

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?

No output schema exists, so the description could reasonably say more about what a drift result contains and what units the thresholds use. Given it is a read-only analytical tool with three parameters at 0% schema coverage, the definition is adequate but leaves real gaps.

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 coverage is 0%, so the description carries full burden and only partially compensates. It supplies default values (0.20/5.0) for the two thresholds but never names them, leaving the agent to guess which number maps to score_threshold versus row_ratio_threshold; dataset_id is unexplained.

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?

States a specific verb+resource with scope: drift computed between the two most recent scans of a dataset. The 'two most recent' qualifier implicitly distinguishes it from drift_compare, but the sibling is never named, so the agent must infer the boundary itself.

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?

It gives the precondition under which the tool fails (fewer than two completed scans), which is genuinely useful implicit usage guidance. It does not, however, say when to choose this over drift_compare, which is the most plausible alternative for the same task.

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