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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world). The description adds genuine behavioral context beyond them: the fallback-to-global-defaults behavior, which tells the agent results may not be org-specific, and the ENTERPRISE+ tier requirement, which explains potential authorization failures.

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 short sentences, front-loaded with what the tool returns before the fallback nuance and the tier caveat. Nothing is padded or repeated for its own sake.

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 full annotations, a fully described single param, and no output schema, an agent has what it needs to call this correctly. The tier gate and fallback behavior are covered; only the shape/ordering of returned criteria is unstated, which is a minor omission for a simple list 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 100% and the single gate parameter is fully documented with its enum values, so the schema carries the meaning. The description's inline enumeration of the same three gates duplicates rather than extends that information, so the baseline 3 applies.

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 and resource (list evaluation criteria) and bounds it to a governance gate, naming the three valid gates inline. An agent can immediately distinguish this from create_evaluation_criterion and update_evaluation_criterion, which mutate the same resource.

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 fallback sentence ('falls back to global defaults when no org-specific criteria exist') gives useful context about results, but the description never says when to reach for this tool versus list_readiness_criteria or the gate-reviewer tools, nor whether the gate filter is the intended first call. Usage is implied rather than stated.

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