drift_compare

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

Annotations already declare readOnly, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: the threshold defaults (0.20/5.0) and their correspondence to the CLI flags, which are absent from the schema.

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?

Two sentences, front-loaded with the core comparison scope and then the threshold details; little waste. The trailing 'D1-06' ticket reference adds noise without meaning for an 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?

For a read-only tool with no output schema and four undocumented parameters, the description covers the drift dimensions and threshold defaults but omits the meaning of the two run-ID parameters and any hint at the response shape or how drift is reported.

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 0%, so the description must carry the parameter burden. It supplies defaults and CLI equivalents for row_ratio_threshold and score_threshold, but says nothing about the semantics of reference_run_id versus current_run_id beyond the phrase 'two historical scans'.

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 gives a specific verb (compare) and resource (two historical scans of a dataset), and enumerates the four drift dimensions: schema, row-count, score, and issue-distribution. It implicitly distinguishes itself from drift_latest by requiring two run IDs, but never names a sibling to differentiate explicitly.

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?

There is no statement of when to reach for this tool versus comparison_build or drift_latest, and no prerequisites or exclusions are given. The mention of CLI-equivalent thresholds describes behavior, not usage conditions.

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