project_undo_group

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

With no annotations provided, the description carries the full behavioral burden. It discloses the undo scope, the conditional dependency on the prior undo step's origin, the no-op fallback behavior, and the exclusion of earlier runs. This gives an agent an accurate mental model of side effects.

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 concise and front-loaded with the core purpose in the first sentence. Every subsequent sentence earns its place by explaining the condition, fallback, and exclusion. No redundant or filler content is present.

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 no-parameter, no-output-schema tool with no annotations, this description is complete. It tells an agent what the tool does, when it applies, what happens when it doesn't apply, and how it differs from the related project_undo tool. Nothing needed for correct invocation is missing.

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 accepts zero parameters and the schema is empty, so there are no parameter semantics to clarify. Following the baseline for zero-parameter tools, this is appropriately handled; the description focuses on behavior rather than inputs.

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 verb and resource: 'Undo every step of the most recent multi-command tool run.' It also names concrete examples like engine_mix and chop_pipeline and distinguishes itself from project_undo, so an agent can tell exactly what this tool does relative to siblings.

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 explicitly says when to use the tool (after a multi-command run), when not to use it (if the last undo step is not from such a run), what happens in that fallback case (changes nothing and directs to project_undo), and that earlier runs are left alone. This is model guidance.

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