list_checkpoints

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

With no annotations, the description itself conveys a non-mutating 'List' behavior and the newest-first ordering. It adds useful behavioral context, though it does not mention limits or what checkpoint fields are returned.

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?

Five words state the operation, object, and sort order with no filler. Every word carries meaning and the main action is front-loaded.

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 parameterless read-only list tool, the description covers action and ordering. Since there is no output schema, a bit more detail on what checkpoint data is returned would be ideal, but it is not required for successful invocation.

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?

There are zero parameters, so the schema has no burden and the description does not need to document arguments. The baseline 4 applies because a no-parameter tool cannot gain meaning from parameter descriptions.

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?

Identifies the exact operation (list), the resource (saved checkpoints), and the result ordering (newest first). This clearly distinguishes it from save_checkpoint and restore_checkpoint and from the various pattern/fabric list tools.

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 the tool is for reviewing saved checkpoints, and the sibling set contains save/restore as related alternatives. However, it does not explicitly state when to choose this over restore_checkpoint or when not to use it.

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