production.create_checkpoint

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

Annotations already declare write semantics (readOnlyHint=false), non-destructiveness, and non-idempotency, so the safety profile is covered. The description usefully adds that four artifacts are persisted, but it omits where they are written, whether repeated calls stack new checkpoints, and any prerequisites such as an unsaved or modified scene.

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 front-loaded sentence with no filler; the verb and the produced artifacts come first. It is efficient, though the extreme terseness is part of why the parameter and usage gaps remain.

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 persistent, non-idempotent write operation with an output schema and a direct sibling (restore_checkpoint), the description should say something about storage location, workflow timing, or undo/restore relationship. None of that is present, so an agent knows what it saves but not how or when to invoke it.

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% across three parameters, so the schema contributes only names and types. The description compensates for none of this: it never explains what 'description' should contain, what 'operation' scopes, or what 'operation_id' links to, leaving the required parameter semantically undefined.

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 specific verb ('Save') and precisely enumerates the artifacts produced: a .blend copy, provenance, a snapshot, and a SHA256 manifest. That makes the operation distinguishable from pure-read siblings, but it never names or contrasts with restore_checkpoint, the obvious counterpart in the toolset.

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 statement of when to take a checkpoint (e.g., before a risky mutation) or when not to, and no routing to alternatives such as restore_checkpoint or diff_scene. The agent must infer the workflow position of this tool entirely on its own.

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