Preview restoring a recovery checkpoint

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

Annotations declare readOnlyHint=true and destructiveHint=false. The description adds significant behavioral detail: the tool only returns a proposal, does not write, handles missing target files with specific revision matching, and restores only the document (not referenced files). 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 reasonably concise at four sentences, front-loading the key action. It packs essential details without excessive verbosity, though the first sentence is somewhat long and could be split for clarity.

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 tool has an output schema for return values, the description covers core behavior, scope limitation, and missing file handling. Minor gaps include lack of explicit prerequisites (e.g., checkpoint existence) and multi-step process context, but these are inferable from sibling names and overall workflow.

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 50% (only expectedRevision has a description). The tool description does not explain the parameters, missing checkpointId meaning entirely. It mentions 'pins the current target revision' which relates to expectedRevision but is not explicit. Description fails to add value over schema.

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 validates a checkpoint, pins a revision, and returns a destructive restore proposal without writing. It distinguishes itself from sibling commit/discard tools by emphasizing 'without writing' and only restoring the specific document, not referenced files.

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 implies usage for previewing before commit and addresses edge cases like missing files. It provides clear context but does not explicitly state when to use versus alternatives like tiled_preview_prepared_checkpoint_commit, though the read-only nature and 'proposal' wording serve as implicit guidance.

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