history_restore

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

Beyond annotations (readOnlyHint false, destructiveHint false), the description adds that it creates a new revision and preserves history, clarifying the additive nature. It also implies a concurrency check via expected_revision. However, it does not mention failure modes or side effects on the current working revision.

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 a single, concise sentence with no irrelevant information. It efficiently covers the core action, key requirements, and a critical behavioral guarantee (preserves history).

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?

While the purpose is clear and the output schema is present (so return values are not needed), the description lacks details on when to use the tool, what happens to the current state, and potential error conditions. The requirement of expected_revision is a critical precondition, but other context is sparse.

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 schema has zero description coverage for parameters. The description mentions 'expected_revision' but does not explain 'target_revision', 'project_id', or 'summary'. It fails to map each parameter to its role, leaving the agent to infer that 'target_revision' is the revision to restore and 'summary' is likely a commit message.

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 tool's purpose: restoring a committed revision by creating a new revision. It distinguishes itself from siblings by emphasizing the non-destructive, additive nature (preserves history) and the requirement for expected_revision, making the action unambiguous.

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 provides a precondition (requires expected_revision) but offers no guidance on when to use this tool versus alternatives like history_list or project_update. It lacks contextual cues for selecting this tool over others.

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