checkpoint_run

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

Annotations already indicate the operation is non-read-only, idempotent, and non-destructive. The description adds the side effect of creating an explicit checkpoint, but does not explain overwrite behavior, persistence details, or any required permissions.

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?

A single sentence with no filler, front-loading the action and outcome. Every word contributes to understanding the tool's purpose.

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 tool with two required parameters and no schema descriptions, the description is too sparse. The agent still needs to infer how to construct state_patch_json and which run_id to target, and no usage context is given.

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 description coverage is 0%, so the description needed to compensate, but it only loosely references 'state patch'. It does not explain the required format of state_patch_json or the meaning/role of run_id beyond what the parameter names imply.

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 gives a specific verb ('Apply') and resource ('state patch'), and states the outcome ('create an explicit checkpoint'). This clearly distinguishes it from sibling run-management tools like create_run and resume_run.

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?

There is no guidance on when to use this tool versus alternatives. The phrase 'small state patch' implies a use case, but no conditions, exclusions, or sibling comparisons are provided.

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