start_embeddings

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

With no annotations, the description carries full responsibility for behavioral disclosure. It only states the action (compute embeddings) but omits key traits such as side effects, required permissions, idempotency, runtime expectations, or whether data is read-only or modified. This is insufficient for a computational 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?

The description is a single, front-loaded sentence with no wasted words. It is concise but lacks any structural elements (e.g., parameter highlights, usage notes). Given the complexity, some expansion would be beneficial without sacrificing conciseness.

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 11 parameters, no schema documentation, no annotations, and no parameter explanations in the description, the description is severely incomplete. It does not explain return values (even though output schema exists), parameter roles, or how this step fits into the larger pipeline. The agent would need significant external knowledge to use this tool 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% (none of the 11 parameters are documented beyond names/types). The description provides zero parameter-level meaning, leaving the agent to guess the role of required fields like models_path, dataset_localization, datasets_root, and short_name, as well as optional ones.

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 uses a specific verb 'Launch' and clearly identifies the resource 'Stage 4: compute sulcal embeddings across all 56 model folds (28 regions × 2 hemispheres)'. It distinguishes this tool from siblings (other start_* stages and pipeline tools) by naming the exact computation and scope.

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?

No guidance on when to use this tool versus alternatives like start_pipeline or other stages. The description does not indicate prerequisites, ordering, or when not to use it. With siblings covering different pipeline steps, the agent needs more context to decide correctly.

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