create_annotation

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

With no annotations, the description carries full burden. It discloses that the name is optional and auto-generated, and clarifies annotations are not 3D objects. However, it does not mention side effects, permissions, or limitations (e.g., maximum count, persistence). Adequate for a simple creation tool but not fully transparent.

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 concise with a clear structure: purpose sentence, explanatory paragraph, then Args/Returns sections. Every sentence adds value; no redundant or irrelevant information. Front-loaded and efficient.

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 single-parameter tool with an output schema, the description sufficiently covers purpose, parameter, and return value. It lacks details on how the annotation interacts with other tools (e.g., layers, strokes) but that may be handled by sibling tool descriptions. Slightly incomplete but adequate.

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 has 0% description coverage, so the description must compensate. It explains the 'name' parameter: optional, auto-generated if empty. This adds meaningful context beyond the schema, helping the agent understand the parameter's purpose and behavior.

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 clearly states the tool creates an annotation data block, explains it as viewport overlays for marks/notes/guides, and distinguishes it from Grease Pencil objects. This is a specific verb+resource with good context and differentiation from sibling tools like add_annotation_layer.

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 explains what annotations are and how they differ from Grease Pencil, but it does not explicitly state when to use this tool versus alternatives like add_annotation_layer or add_annotation_stroke. No guidance on prerequisites or non-use cases. Adequate but lacks explicit differentiation.

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