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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and closed-world, so the safety profile is covered structurally. The description contributes nothing beyond that: it does not say what a drift verdict looks like, whether thresholds apply, what the model_id must reference, or what happens with empty windows. With annotations doing the work, this is a clear miss on added behavioral context.

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?

It is short, but brevity here is under-specification rather than conciseness — there is no front-loaded statement of purpose to build on. The internal codename consumes the limited space that could have carried meaning.

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?

A three-required-parameter statistical-drift tool with two nested objects, no output schema, and no parameter documentation needs a real explanation of inputs and verdict semantics. The description supplies none of it, leaving an agent unable to construct a valid call without guessing the window object shape.

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% for all three required parameters, and two of them (reference_window, current_window) are nested objects whose shape is entirely undisclosed. The description offers no clue about the expected structure of those windows (time range? sample set? metric map?) or the format of model_id. This is the exact case where the description must compensate and it does not.

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 is essentially the tool name plus an internal codename ("DriftGuard check (DRG-100-DriftBound)"), restating the title rather than explaining what a drift check does, what is checked against what, or what it returns. The "[trust]" tag hints at a domain but conveys no operation. An agent cannot distinguish this from siblings like drift_certificate or agents_semantic_diff on the basis of this text.

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 guidance on when to use this tool, when not to, or how it relates to the many plausible alternatives (drift_certificate, agents_semantic_diff, forge_verify). Nothing signals prerequisites such as needing a prior reference snapshot. The codename adds no selection signal for an agent.

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