start_container

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

No annotations are provided, so the description carries full burden. It transparently discloses bind mounts, default paths, platform-specific behavior, and the return value (session name). It does not explicitly mention side effects or destructive actions, but creating a session is inherently stateful.

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 well-structured with clear section breaks for platforms. It front-loads the purpose. While slightly lengthy due to platform-specific details, every sentence adds necessary context, and there is no redundancy.

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 the tool's complexity (multi-platform, 5 parameters, no annotations), the description covers most aspects: behavior, parameter details, prerequisites, and output. A minor gap is the 'runtime' parameter default 'auto' is not fully explained (how auto-detection works).

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 0%, but the description thoroughly explains each parameter's purpose, defaults, and platform-specific meaning (e.g., sandbox_or_image differs for Derecho vs local). It adds value beyond the raw schema by describing how parameters interact with the runtime.

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 it starts a persistent container session for interactive CESM runs. It distinguishes from siblings like `container_exec` (execution within a container) and `stop_container`. Platform-specific details (Derecho vs local) further clarify the tool's role.

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 provides explicit usage guidance for two platforms, including defaults, prerequisites (e.g., build_sandbox for Derecho), and required parameters (inputdata_dir mandatory on local). It does not explicitly state when to avoid the tool or alternatives, but the context is clear.

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