init_experiment

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

With no annotations provided, the description carries the full burden of disclosure. It states it scaffolds files but does not mention what happens if the output directory already has files (though the 'force' parameter hints at behavior), what specific agent runtime assets are generated, or any side effects (e.g., overwriting). It also does not describe the content of generated files beyond naming them.

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 a single, concise sentence (15 words) that front-loads the core action ('Scaffold a CQ-runnable experiment') and lists key deliverables. No wasted words; every part contributes to understanding the tool's function.

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?

Despite having 5 parameters (some with enums and defaults) and no output schema, the description does not provide enough context to understand the tool's full behavior within the workflow. It does not explain what 'agent' options do, the meaning of 'force', or how this tool fits with siblings like run_experiment. The brief mention of optional components is insufficient for a tool with this complexity.

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?

The description only mentions the 'pyproject.toml' generation, which maps to the 'with_pyproject' parameter, but does not explain other parameters like 'output', 'name', 'force', or 'agent'. The input schema itself has 60% description coverage (3 of 5 parameters have descriptions), but the description adds no extra meaning beyond the schema for these parameters.

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 scaffolds a CQ-runnable experiment and lists key components (cq.yaml, train.py, optionally pyproject.toml, agent runtime assets). This distinguishes it from sibling tools like run_experiment (which runs) and validate_project (which validates). However, the verb 'scaffold' could be more explicit about generating files, and the description could mention that it creates a project structure.

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 gives no guidance on when to use this tool versus its siblings (e.g., when to initialize an experiment vs run or validate). It does not explain prerequisites or outcomes. The name 'init_experiment' implies initialization, but the description should explicitly state that this is the tool to create a new experiment project.

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