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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that each variant is saved as a draft MetricVersion with source='suggestion', that the drafts are returned, and that Stripe-metering hooks fire via ActiveSupport::Notifications. This gives the agent a clear picture of side effects (persistence, metering) beyond the input schema, though it does not mention potential costs or permission requirements.

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 description is three sentences long, each serving a distinct purpose: stating the core action, explaining the persistence behavior and return value, and noting the metering side effect. It is front-loaded with the primary verb and resource, contains no fluff, and is appropriately sized for the tool's complexity.

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?

Given no annotations and no output schema, the description provides sufficient context: the tool's purpose, its side effects (saving drafts), return value (persisted drafts), and an important notification mechanism. It does not explain error conditions or permission requirements, but for a relatively simple tool with three parameters, the description is adequately complete to guide selection and invocation.

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?

The schema already provides strong descriptions for 'count' and 'model', leaving 'metric_id' without a description. The tool description adds context by explaining that the metric's judge instruction is rewritten, which clarifies the role of 'metric_id'. However, the description does not add significant semantic value beyond what the schema already covers, and with 67% schema coverage, it partially compensates but does not fully enrich the parameter meanings.

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 clearly states the tool's function: it asks the model to rewrite a metric's judge instruction in N variants. It specifies the resource (metric's judge instruction), the action (rewrite/generate variants), and the output (persisted drafts). This distinguishes it from sibling tools like metrics_update or prompts_suggest_improvement, which target different resources or actions.

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 description implies usage—'targeted at the recent disagreements' suggests it is for improving a metric after disagreements. However, it does not explicitly state when to use this tool versus alternatives, such as manually editing the metric or using other metric_versions tools. No explicit exclusions or alternative tool references are provided.

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