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

The description adds critical behavioral details beyond the annotations. It clearly states the operation is 'Atomic, undoable', explaining the transaction semantics. It also explains the 'dryRun' parameter as a validation-only mode, and 'expectedRevision' as an optimistic concurrency control. The idempotency is also disclosed: 'repeating an ID updates it', which aligns with the idempotentHint. These details provide the agent with a full understanding of the tool's safety and side effects.

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 highly compact and informative. In just a few sentences it covers the core function, limits, presets, update semantics, asset scoping, atomicity, undoability, dry run, and the absence of a generation pass. It is front-loaded with the most critical info (limit and timing) and avoids redundancy or filler.

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?

Given the tool's high complexity (multiple presets, conditional required fields, nested objects in the items array), the description is remarkably complete. The output schema is present, so the return values are covered externally. The description provides essential operational context: when to call, what it does, its safety properties, and its non-generation scope. Additional per-preset field mapping would be nice but is arguably beyond the description's scope; the schema already provides that detail.

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 schema covers only 40% of parameters in descriptions, so the description must compensate. It does not explain every parameter, but it does clarify the 'dryRun' semantics (validates without writing) and the revision/expectedRevision behavior. It also clarifies 'items' as a list of visual blocks. The core behavioral parameters are explained, which is a strong compensation for the schema's gaps.

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 specifies a clear verb ('Create or update'), a definite resource ('visual blocks'), a concrete limit ('up to 20'), and lists the exact presets. It also emphasizes that IDs are scoped to the project and that repeating an ID updates it, which distinguishes it from tools that create new items.

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 explicitly states WHEN to use this tool: 'after edit timing is settled'. It names the presets and clarifies that asset IDs must belong to the workspace. It also clearly signals a non-use case with 'No generation pass', telling agents this is not for generating content, which is a clear exclusion. Alternatives are not named, but the context is strong enough to differentiate from many sibling tools.

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