create_experiment

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

With no annotations provided, the description carries the full burden. It discloses that it does not run and that tool commands come from operator config, but it does not explain side effects like file creation, permissions, reversibility, or what the return value looks like. This is minimal transparency for a tool that likely writes configuration files.

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 three short sentences, front-loaded with the main action 'Prepare input files.' It is concise and does not waste words, though the final clause about 'Native batch folder, not an SWB project' adds context without being verbose.

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?

For a tool with four required parameters including nested objects and no output schema, the description is incomplete. It does not explain the required format for files and stages, the meaning of run_id and project, or what happens after execution. It also lacks guidance on when to use it versus siblings, making it insufficient for an agent to call correctly without additional knowledge.

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%, so the description must compensate. It only hints that stages contain tool and input_file, but it does not explain project, run_id, or the structure of files. The description adds almost no meaning to the parameters beyond what the schema already shows, leaving most parameter semantics undocumented.

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 states a specific action 'Prepare input files' and explains that stages specify tool and input_file, which clarifies the creation/configuration nature. It also distinguishes itself from running tools by explicitly stating 'Does not run.' However, the description does not explicitly say it creates an experiment record, which might be ambiguous given the tool name, but it is clear enough for a setup step.

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 context: it prepares input files and does not run, so it is used before submit_experiment. It also mentions 'Native batch folder, not an SWB project,' which hints at environment suitability. However, it does not explicitly name alternative tools or provide when-not-to-use conditions, leaving some inference required.

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