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

The description discloses important behavioral details beyond annotations: 24-hour serving window, random slug, update_preview resetting the clock on the same URL, and the 5-preview limit on free accounts. This meaningfully informs the agent of lifecycle and side effects.

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 paragraph is dense but every sentence earns its place: it covers the address format, expiration behavior, update preference, use-case guidance, and account limits. Information is front-loaded and there is no filler.

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 tool's purpose, lifecycle, alternatives, and constraints well. It does not explicitly state what the invocation response contains, but it gives the address pattern and the schema is rich enough for a competent agent to proceed.

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 description itself adds little parameter-level detail, but the input schema contains rich nested descriptions for files, path, sha256, content, encoding, and sourceUrl. The schema effectively carries the parameter semantics, so the description's lack of field detail is acceptable but not exceptional.

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 states the exact verb and resource: 'Publish files as a TEMPORARY preview' at a concrete address pattern. It clearly distinguishes this from permanent site publishing and from update_preview by emphasizing temporariness.

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?

It gives explicit when-to-use guidance: 'Use this for drafts, iterations, and unclear intent' and prefers updating an existing preview unless a fresh address is needed. It even names the alternative behavior and explains that a preview is the 'cheap mistake'.

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