run_experiment

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

Without annotations, the description carries full burden. It discloses log capture and environment setup but omits key behavioral details like synchronous/asynchronous execution, error handling, return value, and potential side effects. This is a moderate gap.

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 concise (3 sentences) with the core action in the first sentence. However, the use of jargon ('cq.yaml.cmd', 'CQ_CONFIG_JSON en'v) slightly reduces accessibility. Overall, it is well-structured and focused.

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 lack of annotations and output schema, the description is incomplete. It does not explain prerequisites (e.g., experiment initialization), return values, concurrency behavior, or failure modes. For a tool that executes a command, these details are important for safe and correct use.

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 50% (only 'config_only' has a description). The tool description adds no extra meaning for either parameter. For 'path', there is no description at all, and for 'config_only', the schema already explains it. The description does not compensate for the missing parameter documentation.

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 the tool executes 'cq.yaml.cmd' with an auto-wired environment and captures logs, which maps to the tool name 'run_experiment'. However, it relies on the agent understanding the specific file and environment, slightly reducing clarity.

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 explicitly advises to 'prefer the CQ service queue' for long-running GPU training, providing a clear when-not-to-use guideline. It does not directly compare to sibling tools but offers useful usage context.

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