create_checkpoint

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

With no annotations, the description takes on the full behavioral burden and does so thoroughly. It discloses retention limits, cleanup timing, potential effects on the project path and scene, file-writing behavior, the need to verify state, and the ambiguity of timed-out operations. This is substantially more transparency than most tool descriptions provide.

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 and front-loaded, starting with the core action. Every sentence adds distinct value: retention policy, cleanup behavior, side-effect warnings, verification guidance, and retry handling. There is no redundant or filler content.

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?

The description covers the most important operational concerns: safety, side effects, retention, cleanup, and timeout ambiguity. It does not describe what the tool returns, but the 'Verify resulting state' guidance partially mitigates that gap. Given the risky nature of the operation, this is a well-rounded 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 only parameter, label, is required, yet the description never explains what label should contain, whether it must be unique, or how it relates to the checkpoint. Schema description coverage is 0%, so the description needed to compensate for the missing parameter documentation, but it does not.

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 states a specific action ('Save a unique ZPRJ checkpoint') on a concrete resource, making the tool's purpose immediately clear. It also implicitly distinguishes this from durable saves by describing the checkpoint as an auto-cleaned cache, so an agent can tell it apart from save_project and restore_checkpoint.

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 gives explicit when-not-to-use guidance: 'Keep durable project saves outside this auto-cleaned cache.' It also provides a post-timeout procedure, telling the agent to call reconcile_operation before retrying. It does not explicitly name sibling tools like restore_checkpoint or save_project, but the exclusion of durable saves is strong context.

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