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

With no annotations, the description carries the full burden; it usefully discloses reuse behavior (idempotent-ish start) and the nature of what is returned (a private link for a human). It does not state auth/permission needs, whether the preview consumes credits, or what happens if the build doesn't exist.

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?

One sentence, front-loaded with the action and followed by the returned URLs; every clause carries information. Slightly run-on but no waste.

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?

Because there is no output schema, the description usefully enumerates the return values (previewUrl, workspaceUrl, sourceUrl), which is a real contribution. The gap is the undocumented sessionId input, leaving the calling contract partially unclear.

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 coverage is 0% and the single required parameter (sessionId) is never mentioned in the description. The description does not explain what a session id is or where to obtain it, so it fails to compensate for the documentation gap.

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 gives a specific verb+resource ('Start (or reuse) the live preview for a build') and names the return artifacts. It distinguishes itself from build-lifecycle siblings like codebase_start_build and codebase_get_build_status by focusing on the preview link, though it never names those alternatives explicitly.

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 parenthetical '(or reuse)' implies this is safe to call when a preview may already exist, which is useful implicit guidance. However, there is no explicit when-to-use vs alternatives, no prerequisites, and no statement of when this should be called relative to codebase_start_build or codebase_get_build_status.

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