design_system_apply

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

Annotations already declare destructiveHint=true dar. The description adds meaningful behavior: it explains that literal styles are preserved unless mapping explicitly binds them, and that token bindings resolve against the new version. It also frames the operation as a 'guarded revision', implying atomicity/concurrency protection. This goes beyond annotations and is valuable for a write operation.

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?

Two sentences, no filler. The action is front-loaded, and the subsequent sentence adds critical behavioral nuance without verbosity. Every clause earns its place; the description is compact and readable.

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?

The description covers the central semantic behavior of the tool but omits operational context needed to call it correctly. It does not explain the required guard parameters (expectedRevision, digest, operationId) or what 'guarded revision' means in terms of failure modes. Given the complexity (8 params, nested mapping, destructive), the description is incomplete even with annotations present.

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%, and the description only hints at two of the eight parameters: mapping (via 'mapping explicitly binds element properties/page backgrounds') and version (via 'chosen new version'). Core parameters like id, digest, documentId, operationId, actor, and expectedRevision are left unexplained slopes. For a destructive tool with zero schema descriptions, this is insufficient.

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 names a specific verb+resource: 'Apply or upgrade a saved design system to a document'. It also mentions it's 'one guarded revision', which adds a clear operational scope. It does not explicitly distinguish itself from siblings like design_system_preview or document_apply, but the action and target are unambiguous.

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 implies usage: when you want to apply/upgrade a design system to a document. It also clarifies what happens to literal styles and token bindings, which helps decide whether this tool fits. However, it provides no explicit when-not-to-use guidance or comparison to sibling tools (e.g., when to use design_system_preview first).

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