grease_pencil.create

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

The description discloses only risk level and maturity, not the actual behavior of the tool. Annotations are all false and provide nothing, so the description must carry the behavioral disclosure. It never says what side effects occur or what gets created, making it impossible for an agent to reason about consequences.

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 short, but brevity is not the issue; it is under-specified. The sentences about risk and maturity could be informative for safety but do not help with tool invocation. In this form, the description is not 'concise commentary of purpose' – it is missing the purpose entirely.

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?

With 7 parameters, 2 required, and no output schema shown, an agent has no information about what input values should be, what the tool returns, or what a successful call looks like. All forced parameters (name, _transactionId) are undocumented. The tool definition fails to provide essential context for its complexity.

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 only 43%, and the parameters lacking descriptions (name, layers, inFront, _expectedSceneRevision) are not documented in the description either. The description adds zero meaning beyond the schema, and the schema itself omits descriptions for most parameters, leaving the agent without guidance.

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 only restates the harness command name and meta-information; it never states what the tool actually does. The action verb 'create' exists only in the tool name, so the description is effectively a tautology with no resource or operation specified.

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. It does not mention whether to use it to create a grease pencil object, how it differs from grease_pencil_add_stroke, or any conditions for using it over other creation tools. The description is entirely meta-information.

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