restore_version

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

With no annotations, the description carries full behavioral burden and does so: it discloses that the restore is non-destructive (saved as a NEW version, no reset, no deleted history, later-added files kept) and states a refusal condition for dirty state. This is exactly the mutation-safety context an agent needs.

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 core purpose and non-destructive guarantee are front-loaded, and every sentence carries useful information about workflow or safety. It is dense and long, but no sentence is wasted; slightly tighter phrasing would help.

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 need no explanation, and the description covers purpose, safety, prerequisites, and the multi-step workflow including the server case. Nothing essential to 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?

Schema coverage is 0%, so the description must compensate: it explains 'version' can be a number from list_versions(part) or a commit id, which is real added meaning. 'part' is only implied by the examples (script, ref/, MEASURE.md) rather than defined, leaving a small gap.

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?

States a specific verb and resource ('Bring a part back to a saved version') and enumerates what a part is (script, ref/, MEASURE.md). It distinguishes itself from siblings by naming list_versions as the version source and save_version as the pre-step.

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?

Explicit prerequisites and sequencing: refuse while unsaved changes exist, offer save_version first, ask the user before restoring, then build_part and check. Even the shared-server workflow routes the agent to write_part, leaving little to inference.

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