Preview committing an ambiguous prepared recovery checkpoint

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

Annotations already provide readOnlyHint=true. The description adds valuable behavioral details: it pins the manifest, requires exact match, returns a proposal without modifying assets, explains the effect of applying the proposal, and clarifies that it cannot restore as deletion. No contradiction with annotations.

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 compact yet comprehensive. Every sentence adds necessary information without redundancy. It is front-loaded with the core purpose and scales to behavioral specifics. No wasted words.

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 the single parameter, clear annotations, and the presence of an output schema (inferred), the description covers all essential aspects: when to use, what it does, what it returns, and what it avoids. It is fully adequate for an AI agent to invoke correctly.

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 one parameter (checkpointId) with 0% description coverage. The description adds context by specifying that the checkpoint must be from an ambiguous create, providing meaning beyond the schema's UUID pattern. However, it does not elaborate on the parameter's syntax or format.

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 it is a preview of committing an ambiguous prepared recovery checkpoint. It specifies the action verb 'preview' and the resource 'ambiguous prepared recovery checkpoint', distinguishing it from sibling preview tools like discard or abandon.

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 explicitly limits usage to 'for an ambiguous create checkpoint only', indicating when to use. It explains the return of a proposal without changes, and what it does not do (no garbage collection, no force flag). While it does not explicitly compare to siblings, the naming and context make it clear this is for the commit preview.

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