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

With annotations providing only mutability flags (readOnlyHint=false, etc.), the description carries the burden of behavioral disclosure. It adds critical context: creates or updates a service, includes health checks and public HTTPS URL, autoscales between min and max instances, scale-to-zero when min=0, and per-vCPU-hour billing. No contradiction with annotations; openWorldHint is consistent with creating external resources.

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 four sentences, each earning its place: the first defines the operation, the second details feature set and revision behavior, the third covers pricing, and the fourth points to rollback. No fluff, no redundancy, and the most important action is front-loaded.

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 complex deployment tool with 6 parameters and no output schema, the description covers the core behavior (create/update), key features (health checks, public URL, autoscaling), cost implications, and a rollback safety net. It does not explain return values, but with no output schema that is not required. The only minor gap is not mentioning the build prerequisite, but that is covered in the image parameter's schema description.

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 100%, so baseline is 3. The description adds value by clarifying the relationship between min_instances and max_instances ('autoscaling between...') and the billing implication ('Billed per vCPU-hour while instances run'), which gives cost context to instance counts. The image parameter's external-registry restriction is already in the schema, so the description does not need to repeat it.

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 opens with a specific verb+resource pairing: 'Deploy a long-running container service on Scalix Run from a container image.' It clearly distinguishes this tool from serverless function deployment (scalix_fn_deploy) by emphasizing long-running containers, and from rollback by naming scalix_run_rollback. The behavior of creating a new service or a new revision is explicit.

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 states the primary use case ('deploy a long-running container service') and explicitly points to scalix_run_rollback for undoing a bad revision. It does not explicitly contrast with scalix_run_scale or scalix_build_create, though the schema hints at the build prerequisite. Clear context but lacks explicit when-not-to-use alternatives.

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