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

Annotations already declare destructiveHint=true and the title says 'mutates infra'; the description reinforces this with 'MUTATING:' and the POST endpoint. It does not add deeper behavioral context such as consequences of reducing replicas, scale-to-zero effects, or whether scaling is asynchronous, but the annotation covers the main safety signal.

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 a single front-loaded sentence with the mutating nature, the exact operation, and the HTTP endpoint. Every element is useful and there is no filler.

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 simple three-parameter tool with all parameters documented and destructive behavior already annotated, the description provides the essential operation and endpoint. It could mention side effects of decreasing instances or scaling to zero, but the annotations and schema carry most of the required context.

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 all three parameters are already fully described in the schema. The description only echoes projectId and serviceId in the endpoint path, adding no new semantic information about parameters.

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 states a specific verb and resource: 'set the number of running instances (replicas) for a service.' It also includes the exact endpoint, which distinguishes it clearly from sibling get/list tools and from pause, resume, and restart mutations.

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 operation itself implies when to use it—when you need to change replica count—but there is no explicit guidance contrasting it with pause_service, resume_service, or restart_service. No when-not-to-use or alternative selection criteria are provided.

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