Start Training

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

With no annotations, the description carries the full burden. It does disclose useful behavior: the config prerequisite and the exact default-resolution rules for config_dir/output_dir across roots vs pipeline modes. It is silent, though, on overwrite semantics, whether training is async/job-backed (relevant given get_job_status/list_jobs siblings), and resource/permission expectations.

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 purpose is correctly front-loaded in the first sentence, and the prerequisite follows logically. The remainder is a dense, repetitive paragraph dedicated almost entirely to config_dir path resolution while the other seven parameters get nothing, which is an imbalanced use of space.

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?

An output schema exists, so return values need not be described. But for a 9-parameter, annotation-free tool, leaving cpu, swf, mode, njobs, and overwrite entirely unexplained is a material gap an agent needs to invoke it correctly.

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% across 9 parameters, so the description must compensate. It thoroughly explains config_dir (and indirectly output_dir), but cpu, swf, mode, njobs, and overwrite receive no explanation at all, leaving the majority of parameters undocumented in both schema and description.

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 gives a specific verb (launch/train), a concrete resource (champollion_V1 self-supervised encoder), and a clear scope (one sulcal region), so an agent can distinguish it from start_config or start_embeddings. It does not explicitly name a sibling to differentiate from, which keeps it below a 5.

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?

It states a strong prerequisite ('Dataset configs must exist before calling this tool: run start_config first'), which is genuine ordering guidance. However, it never says when to choose this over alternatives like start_embeddings or start_pipeline, so the when-vs-alternatives dimension is only implied.

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