altair_split_data

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action without explaining behavior: whether the split is random, if it modifies the original data, or any side effects like creating new repository entries. The internal action number '66' adds no behavioral context.

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 extremely concise, consisting of two sentences with no wasted words. It front-loads the primary purpose and includes a secondary reference to an internal action identifier, which is brief but does not clutter the description.

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's complexity (splitting data for machine learning), the description is insufficient. It lacks details about the split strategy (e.g., random, stratified), reproducibility (no seed parameter), handling of imbalanced classes, or output format. Absence of output schema and annotations exacerbates the lack of completeness.

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?

The input schema already documents two of three parameters (csvFile and repositoryEntry) with descriptions of their usage and mutual exclusivity. trainRatio has default and range constraints. The description adds no parameter-specific information beyond what the schema provides. With 67% schema coverage, a baseline of 3 is appropriate.

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 splits a dataset into train/test partitions, which is a specific verb+resource. However, it mentions 'train/validation/test split' in parentheses, which is slightly different from the main description but still conveys the core purpose. It distinguishes from sibling tools like altair_clean_data or altair_normalize_data because splitting is a distinct operation.

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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as the need for a dataset already in the repository or local file, or any conditions under which splitting is appropriate. There is no comparison with other data manipulation tools.

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