train_preview_config

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

With no annotations provided, the description carries full behavioral disclosure burden. It states 'no side effects', which is key for a preview tool. No mention of auth, rate limits, or output details, but the core safety trait is covered. Could add more context about permissions or input validation, but sufficient for this tool.

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?

Two sentences: first explains the action and side-effect nature, second gives usage context. No filler, every sentence adds value. Front-loaded with the core purpose.

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 has no output schema and 4 parameters, the description covers purpose, usage, and key parameter context. It explains the output is the raw config YAML, which is sufficient for an agent to understand the return. Lacks explicit mention of output format details, but overall complete for a preview tool.

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 100% with each parameter having a description. The description adds meaning beyond the schema by explaining that parameters are the same as those for train_start and that datasetPath comes from specific sibling tools. This helps the agent understand parameter relationships and sources.

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 displays the raw config that train_start would write, with no side effects. It uses specific verbs ('Show', 'review/edit') and identifies the resource (config.yml). It distinguishes from the sibling train_start by mentioning 'preview' and 'no side effects'.

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 second sentence explicitly says 'Use it to review/edit a run before launching; pass the same params to train_start to execute.' This gives clear when-to-use guidance. However, it does not mention when not to use or provide explicit alternative tools, though the intended use case is well understood.

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