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

readOnlyHint=true already covers the safety profile, so the description's contribution is naming the computed statistics and noting the call is free. It says nothing about authorization needs, rate limits, or whether an unknown model produces an error versus an empty report.

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?

One front-loaded sentence with no filler; the metric list is dense but each term earns its place. The trailing 'Free.' is a fragment but conveys a real cost signal.

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?

With no output schema, no annotation detail, and 0% schema coverage, the description should explain what the report looks like (units, thresholds, drift definition) and what task_type does. Neither is addressed, which is a meaningful gap for a two-parameter analytical tool.

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 both parameters. 'For one model' hints at the required `model` argument, but `task_type` is never mentioned anywhere, leaving half the parameters undocumented.

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 resource (calibration report for one model) and enumerates the concrete metrics returned (Brier, ECE, reliability bins with Wilson intervals, overconfidence, drift). It doesn't name a sibling, but 'for one model' implicitly contrasts with court_leaderboard's multi-model view.

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?

No statement of when to use this versus court_leaderboard, court_recalibrate, or court_calibrate_labels. The only usage-adjacent signal is 'Free', which speaks to cost, not to when the tool applies.

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