container_exec

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

With no annotations, the description bears full burden. It states the command runs inside a container and returns stdout+stderr, but does not disclose side effects, authentication needs, or error behavior. It does not mention that the container must be running (implied by 'running container session'), nor any potential destructive actions.

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 short and front-loaded. It uses a list format for parameters, which is clear. Every sentence adds value, though the runtime parameter could be better integrated. No redundant information.

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 presence of an output schema explaining return values, the description is fairly complete. It explains critical platform-specific behavior for case_dir. However, it omits details about the runtime parameter and error handling, which would improve completeness.

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 0% but the description adds meaning for name ('session name from start_container'), case_dir (path details with platform differences), and command (examples given). The runtime parameter is mentioned only as default 'auto' with no explanation. Coverage is partial but adds value.

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 'Run a CIME command inside a running container session.' This distinguishes it from siblings like start_container (which starts a session) and case_build (a specific command). The verb 'run' and resource 'CIME command in container' are 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 implies usage when a container session is running and a CIME command needs to be executed. It provides platform-specific notes for case_dir but does not explicitly state when to use this tool over siblings like case_build or case_submit. No exclusion criteria are given.

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