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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses critical behavioral traits: the URL carries an access token, is view-only, works only if shared exactly as returned, live-updates as you edit, and includes a sandbox API base for headless testing. It also clarifies that Floot hosts the app and warns against external hosting. This is rich context that annotations alone do not provide.

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 intentionally detailed but not overly verbose. It front-loads the core action and then addresses usage caveats, token behavior, live-update nature, and the sandbox API in a logical sequence. Slightly long but each sentence adds value without redundancy.

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 tool has a single parameter, no output schema, and annotations that only cover read-only/destructive hints. The description fully covers all needed information: what the result includes (preview link, sandbox API base), how it behaves (live-updates, view-only), and important constraints (token in URL, not for production, not for external hosting). Nothing an agent needs to call it correctly is missing.

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 only defines projectId as a string with zero description. The description compensates by implying the parameter must refer to an existing project ('on an EXISTING project') and warns against using it right after create_project, which indirectly clarifies the expected input. While it does not explicitly spell out 'projectId is the identifier of an existing project,' the context strongly implies it, adding meaningful guidance beyond the bare schema.

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 clearly states the tool's purpose: 'Show the user a live preview card and return the preview link.' It identifies the resource (preview card/link) and the action (show/return). It distinguishes itself from siblings by explicitly contrasting with create_project (duplicate) and publish_app (production), making the uniqueness clear.

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?

Provides explicit when-to-use guidance: 'typically called EARLY, before the first change' on existing projects. It gives a strong when-not-to-use: 'Do NOT call it right after create_project' because it duplicates the card. Also points to an alternative: 'to go to production use publish_app.' This is exactly the level of guidance expected.

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