start_training

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

No annotations provided, so description carries full burden. Mentions config existence requirement, but does not disclose side effects (e.g., file modifications, resource usage, idempotency, failure behavior). A mutation tool like this should state whether it overrides existing outputs or requires network access.

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, no wasted words. Purpose front-loaded. Could benefit from list format for prerequisites, but overall concise.

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?

With 9 parameters, 0% schema coverage, no annotations, and minimal description, the tool is underdocumented. The output schema exists but description doesn't reference it. Missing details like what 'mode: encoder' implies or what 'overwrite' does. Insufficient for an agent to reliably invoke.

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 description must explain parameters. It only mentions dataset, region, and config_dir. The other 6 parameters (cpu, swf, mode, njobs, overwrite, output_dir) are completely undocumented, leaving the agent guessing.

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?

Description clearly states it launches encoder training for a specific region and model (champollion_V1). The verb 'Launch' plus resource 'encoder training' is specific and distinguishes from siblings like start_cortical_tiles or start_embeddings.

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?

Explicitly provides prerequisite: dataset configs must exist, and mentions run start_config first or supply config_dir. This gives clear guidance on when to use this tool. No explicit when-not-to-use, but helpful context.

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