checkpoint_project

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

With no annotations, the description carries the full burden and does well: it discloses the two side effects (saving the project, writing a new file next to it), the folder location, and the naming template. It also explains the motivation (no undo group for scripts) and recovery procedure, though it omits error behavior and what happens on an unsaved or pathologically named project.

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 dense sentences, front-loaded with the action and side effect, then rationale, then the listing escape hatch. Every sentence earns its place, though the inlined path template is slightly awkward to parse.

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 two-parameter mutation tool with no annotations and no output schema, this covers everything an agent needs: what is written, where, how it is named, why to call it, how to recover, and how to enumerate existing checkpoints.

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 100%, so the baseline is 3, but the description goes further by explaining that list: true switches the tool into list-only mode — a behavioral change the schema's 'Only list checkpoints' phrase only hints at. The label parameter is covered by the schema example, so no further compensation is needed.

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?

States a concrete verb chain (save the project, thencopy the .prproj into a checkpoints folder) and names the exact artifact produced, including the naming convention. This clearly separates it from save_project/save_project_as, which persist the project without producing a versioned copy.

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?

Gives explicit when-to-use guidance: before any large automated change such as a rough cut, aspect versions, or colour layers, plus the restore path (open the copy) and the listing mode (list: true). It doesn't explicitly contrast with the plain save_project sibling, so the boundary is implied rather than stated.

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