cw_history_help

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

With no annotations, the description carries the full burden. It does add genuine domain substance — that the undo stack is the backstop for irreversible writes and that "none-observed" in a window diff is a false-failure signal — but it never states that the tool itself is read-only, side-effect-free, or what form the returned help takes.

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 covering four named topics with no filler, though the nested parenthetical and quoted "none-observed" make it denser and harder to parse than necessary.

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 zero-parameter, no-output-schema help tool, the topic list is sufficient to decide whether to call it. The only missing piece is an explicit statement of what it returns and that it has no side effects, which is minor for a help resource.

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 tool takes zero parameters and the schema has full coverage, so parameter semantics carry no burden; the baseline of 4 applies.

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 opens with a concrete topic statement ("How undo/redo work here") plus a list of the specific subjects covered: undo-stack dialog, irreversibility backstop, and the rewind-verification trap. It is clearly a help/explanation resource, distinguishing it from the action-oriented siblings cw_undo, cw_redo, and cw_history, though it never explicitly says it returns documentation rather than performing history operations.

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?

Usage is only implied: an agent can infer it should read this before relying on cw_undo/cw_redo or before concluding a rewind failed, but no explicit when-to-use statement or routing to/away from siblings is given. Sibling help tools (cw_edit_help, cw_job_help, cw_cal_help) are not referenced as alternatives.

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