history_redo

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

With no annotations, the description carries the full burden. It does disclose one meaningful behavioral trait: expected_head_id guards the operation like history_undo and returns error_code history_stale on mismatch. However, it omits what rerender does, whether it mutates state destructively, and what the return looks like, leaving notable gaps for a mutation tool.

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?

Very short and front-loaded with the core action in the first sentence, then the guard in the second. Efficient, with the only minor cost being the indirect 'like history_undo' reference the reader must resolve.

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?

An output schema exists, so return values needn't be explained, and the guard behavior is covered. But for a mutation tool with no annotations and fully undocumented parameters, the description is incomplete regarding what rerender/project_path do and what state changes occur.

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 0% across 3 parameters. The description partially explains expected_head_id's guard role but says nothing about rerender or project_path, so it does not compensate for the schema gap. Two of three parameters remain semantically opaque.

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?

Specific verb+resource: 'Redo the last undone project mutation.' The word 'undone' clearly distinguishes it from history_undo, and the description explicitly references history_undo as its counterpart. Clear enough for an agent to select it, though it doesn't name which mutations qualify.

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 implied by 'redo the last undone mutation' and the reference to history_undo's guard behavior, but there is no explicit when-to-use/when-not or a statement of alternatives. An agent can infer the redo-after-undo context but must read the sibling to confirm.

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