stack_assign

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

Goes beyond the annotations by disclosing the exact mutation target (`stack` field in service.json), the refusal for already-stacked resources, and that the return value is the command's text output. Slight tension with `idempotentHint: true` — re-invoking on the same input is refused rather than silently succeeding — but this is a disclosed error path, not a contradiction.

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 sentences, front-loaded with the core action and the exclusion, then the return value, then the conditional path parameter. 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?

Covers mutation target, refusal behavior, return type, and path handling, which is sufficient for a 3-param mutation with no output schema. It leaves open what happens if the named `stack` does not already exist.

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 earns an extra point by adding when-to-use semantics for `projectPath` that the schema does not convey. It says nothing extra about `stack` or `resources` beyond the schema's own naming.

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 (assign resources to a stack) plus the mechanism (writes `stack` into service.json) and the restriction (resources already stacked are refused). This is clearly distinguishable from sibling `stack_list` or `resource_create`, though no sibling is named explicitly.

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?

Gives a clear precondition — the resource must have no stack yet — and notes the failure case for already-assigned resources. It also gives a conditional context rule for `projectPath` (when the server isn't run from the project root). It stops short of naming alternatives for assigning/moving resources.

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