restore_reference_doc_version

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

With no annotations provided, the description carries full burden. It discloses key behavioral traits: only the draft is changed, the live version remains untouched until a human approves a publish, and the snapshot ensures undoability. It does not address permissions or failure modes, but the core safety aspects are covered.

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 three sentences, each adding essential information: what it does, important parameter nuance, and behavioral impact. Front-loaded with the action, no redundant or confusing text.

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?

The tool has 3 simple required params and no output schema. The description covers the core operation and its side effects but does not mention return value or error scenarios. Given the tool's straightforward nature, this is adequate but not fully comprehensive.

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 100% with descriptions for all 3 parameters. The description adds value by clarifying versionId is a UUID from list_reference_doc_versions, not a checkpoint number. The other parameters (id, expectedVersion) are well-described in the schema, so the description provides marginal extra meaning.

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 explicitly states 'Roll a reference_doc's DRAFT back to an earlier version,' using a specific verb and resource. It distinguishes from siblings like 'restore_reference_doc' by focusing on draft rollback only, and clarifies it does not affect live content.

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 explains that the versionId must be a UUID from list_reference_doc_versions, not a checkpoint number. It also notes that the current draft is snapshotted first, making the operation undoable. However, it does not explicitly mention when not to use this tool or name alternatives.

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