Preview discarding a prepared recovery checkpoint

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description confirms this by stating it returns a proposal without deleting or modifying assets. The description adds detailed behavioral context (pinning manifest, proving state, rejection conditions) beyond what annotations provide. No contradiction.

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, each adds value without redundancy. The first sentence states the main action and constraints, the second clarifies what does not happen, and the third lists rejection conditions. 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?

For a preview tool with one parameter and an output schema, the description covers purpose, preconditions (target state), and rejection cases. It does not detail the output schema, but that is acceptable since it exists separately. Slight omission: the checkpoint must be in a prepared state, but this is implied by the tool name and description.

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 single parameter checkpointId is described indirectly via 'pins one prepared checkpoint manifest' and the title mentioning 'prepared recovery checkpoint'. The schema has a UUID pattern and is required. While the parameter's role is inferable, the description does not explicitly define it or explain where to obtain the ID. With 0% schema description coverage, more explicit parameter guidance would improve clarity.

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 action: it pins a prepared checkpoint manifest and proves the target state, returning a discard proposal. It distinguishes from siblings (commit, abandon) by specifying that it is for discard preview. The conditions for rejection are listed, making the purpose 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 implies when to use: for previewing a discard operation on a prepared checkpoint. It lists states that lead to rejection, effectively telling the agent when the tool will fail. However, it does not explicitly compare with alternatives like tiled_preview_prepared_checkpoint_commit or abandon, though the name and title provide context.

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