plan_windows

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

Annotations already declare readOnlyHint=true, destructiveHint=false, so safety is covered; the description contributes that the operation is a pure planning/computation over episodes, which is useful. It does not say whether the plan is returned inline, written to disk, or persisted, nor whether window/stride must satisfy constraints against episode lengths.

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?

A single front-loaded sentence with no filler; the core purpose lands immediately. The trailing parenthetical is the only part that fails to earn its place, since it adds ambiguity rather than clarity.

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 four undocumented parameters, no output schema, and no indication of what a 'window plan' looks like or how it feeds submit_job, the definition is under-specified for a tool that sits mid-pipeline. An agent would have to trial-and-error the required path format and the meaning of limit.

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% and the description only gestures at window and stride without explaining their units or interaction, while ignoring path (the sole required parameter) and limit completely. The parenthetical 'episode/start/end' does not correspond to any parameter in the schema and reads as ambiguous or misleading rather than clarifying.

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?

Names a specific verb and object: compute a plan of fixed-length windows over a dataset's episodes. The agent can tell this is a planning/derivation step rather than an execution step, but nothing distinguishes it from the sibling segment_episodes, which sounds like it also operates on episodes.

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?

There is no statement of when this tool should be chosen, no prerequisites (must the dataset be validated or segmented first?), and no mention of how it relates to segment_episodes, submit_job, or validate_dataset. The agent must infer the ordering of the pipeline entirely on its own.

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