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

With no annotations, the description carries the behavioral burden well: it discloses that the operation destroys the version, that published versions are rejected, and offers a workaround. It stops short of saying whether the destroy is reversible/soft-delete or what error/return the agent should expect.

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 tight sentences, each earning its place: the action, the refusal condition, and the alternative. The core purpose is front-loaded in the first sentence.

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 one-parameter destructive tool with no annotations and no output schema, the description covers the essential behavior, guardrail, and escape hatch. Only minor gaps remain (permissions, reversibility, error semantics).

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 coverage is 0% for the single metric_version_id parameter; the description never explicitly says this ID identifies the draft version to destroy, relying on implication. It adds unrelated context (the 'source' distinction) that does not map to any schema field.

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 (destroy) and resource (a draft MetricVersion), plus the exact scope of what qualifies (draft, from either source). It is clearly distinguishable from the sibling metric_versions_publish, which it implicitly contrasts.

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?

Explicitly states when this applies (draft versions, either edit or suggestion source), when it will not work (published versions are refused), and names the alternative path for the published case (publish a different version as current). No inference required.

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