save_data

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

With no annotations, the description carries full burden. It discloses key behaviors: combining y and X into one table, creating parent directories, format details (csv index column, JSON records orient with ISO dates). Missing edge cases like overwrite behavior, but overall informative.

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?

Three sentences, no fluff. Front-loaded with the primary action, then details. Efficient 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?

Given no output schema, description adequately covers what happens (persist to file). It mentions combining y and X, which is crucial context. Could add error handling or file existence behavior, but sufficient for typical use.

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%, but description adds meaning: explains path is destination not controlling format, format controls extension, data_handle must be from specific tools. That adds value beyond the schema definitions.

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 persists target series (y) and exogenous features (X) to a local file, distinguishing it from siblings like save_model or load_data_source. The verb 'persist' is specific and the resource (data behind a handle) is well-defined.

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 mentions typical context (after load_data_source, split_data, or transform_data) and lists supported formats. It lacks explicit when-not-to-use or alternatives, but the context is clear enough for typical usage.

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