bdesign_organization_apply

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

Annotations already declare idempotentHint and destructiveHint, and the description adds genuinely new behavior: the whole operation set is applied atomically, writes are guarded by an expected organization revision, and folder removal demands a preview-derived revision. It still doesn't describe what an agent sees on a revision conflict or what the result contains, which matters for a destructive batch call.

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?

Four short sentences, front-loaded with the core purpose, then the concurrency contract, then the removal caveat, then an exclusion. Nothing is repeated from the schema and every sentence carries operational information.

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 high-complexity destructive batch tool with no output schema and zero schema description coverage, the description covers the concurrency contract well but omits conflict/failure behavior when expectedRevision or previewRevision doesn't match, whether operations execute in order, and whether the response carries the new revision. Adequate but leaves real gaps for an atomic mutation.

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%, so the description carries the burden, and it does explain the intent of three parameters: commandId/idempotencyKey must be stable, expectedRevision comes from organization_get, and previewRevision must match. However, the central 'operations' array (11 oneOf variants, max 500, ordering) and the optional projectId get no explanation at all, so a large share of the surface is left to the schema's shapes alone.

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 ('Apply') and a specific resource ('project folder or Element operations') plus the key property that they are applied atomically, so an agent immediately knows this is a batch mutation tool. It partially differentiates from siblings by pointing at organization_get as the revision source and by ruling out media generation, but it never contrasts with other apply-style tools such as canvas_apply or project_update.

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?

Gives concrete preconditions: supply a stable commandId/idempotencyKey and the organization revision obtained from organization_get, and use a matching previewRevision for folder removal. The negative guidance ('Never generates or uploads media') steers the agent away from the wrong family of tools, but there is no explicit statement of when this tool should be chosen over the other *_apply siblings.

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