restore_policy_version

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

Discloses key behaviors: snapshots the current draft (making it undoable), only affects draft (live stays live), and requires a UUID versionId. With no annotations, the description fully bears the transparency burden and does so excellently.

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?

Three sentences: first states main purpose, second clarifies critical parameter nuance, third explains behavior and scope. No redundant words, front-loaded with the action verb.

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?

Given no output schema and 3 required params, the description covers what the tool does, how it works, and key behavioral details. Lacks explicit mention of return format but is acceptable for a state-changing tool with clear side effects.

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%, each param has description. The description adds significant value by clarifying that versionId is a UUID from list_policy_versions (not a checkpoint number) and explaining the undo mechanism. This goes beyond the schema's basic type info.

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 uses a specific verb ('Roll a policy's DRAFT back to an earlier version') and clearly identifies the resource and action. It distinguishes from sibling restore tools by specifying it targets only the draft, not live or deleted policies.

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?

Explicitly states that versionId must come from list_policy_versions and not a checkpoint number. Clarifies that the operation is undoable (snapshots current draft) and only affects draft, not live policy. Lacks explicit 'when not to use' but context is sufficient.

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