hai_drift_check

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It says 'lightweight' and 'thin wrapper', implying minimal behavior and delegation, but it never states whether the operation is read-only, what side effects occur, what the output contains, or what errors or edge cases exist.

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 text is short and front-loaded, but it is not effectively concise because it omits critical information and repeats the 'lightness' idea in two ways ('Lightweight' and 'thin wrapper'). The brevity reduces utility rather than supporting quick comprehension.

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 an 8-parameter tool with no annotations and a 0% schema coverage, this description is severely incomplete. It does not explain the meaning of a drift check, the role of the inputs, the return behavior, prerequisites, or how it differs behaviorally from hai_check_activity, making correct invocation unlikely.

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% and the description mentions none of the 8 parameters. The agent is left to infer meaning purely from names like session_id and activity_step, with no explanation of criterion_id, trace_events, affected_paths, declares_blocker, or how they relate to the drift check.

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 names a specific action ('check against the mission contract') and identifies the tool as a 'thin wrapper' over hai_check_activity, giving agents a rough sense of its place. However, 'mismatch check' and 'drift' remain underspecified about exactly what is being compared and how.

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 only usage hint is 'thin wrapper over hai_check_activity', which hints at a relationship but does not explain when to prefer this tool over hai_check_activity or any of the other siblings. There is no explicit when-to-use, when-not-to-use, or alternative-routing guidance.

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