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

Annotations cover readOnly=false, destructive=false, openWorld=true, and the description adds behavior those annotations cannot express: drafts are browser-owned/private and expire after 15 minutes or a browser reload. That expiration and ownership detail is exactly the kind of non-obvious lifecycle info an agent needs.

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, zero filler, with the core action plus the non-mutation guarantee front-loaded and the expiration caveat second. Well-sized for the value it carries.

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 10-parameter mutation with nested data/state objects, no output schema, and near-zero schema coverage, the description omits far too much: no explanation of controlToken/expectedRevision/operationID, no mention of what the preview URL or the draft handle is used for next. The lifecycle note is useful but nowhere near sufficient.

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 10% across 10 parameters (7 required, including controlToken, expectedRevision, operationID, action, format). The description explains none of them, so required fields like controlToken and expectedRevision remain opaque.

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+resource (creates a component draft with preview URL) and adds a distinguishing scope clause: 'without changing the live workspace.' That implicitly separates it from create_component/publish_draft, though no sibling is named outright.

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?

No explicit when-to-use or when-not-to-use guidance against siblings like create_component, update_draft, or publish_draft. The draft/preview framing hints at an iteration workflow, but the agent must infer that this is the sandbox step before discarding or publishing.

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