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

Beyond annotations (destructiveHint, readOnlyHint false), the description reveals important behavioral traits: it only prepares a replacement and returns an approval link (not a published URL), requires browser confirmation, requires the existing management key, and leaves expiry unchanged. This is rich operational context that annotations alone do not provide, though it doesn't detail exactly what the destructive replacement will affect.

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 four dense sentences with the core purpose and the critical 'exactly one' constraint front-loaded. Every sentence adds new information about the approval flow, consent, or key requirement, but it is slightly long and could be tightened without losing meaning.

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?

Given the tool's complexity (5 parameters, nested objects, no output schema), the description covers the invocation alternatives, the approval flow, the browser-key requirement, and the unchanged expiry. It doesn't describe the structure of the returned approval link or what to do with it, but that is beyond the immediate call.

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 must compensate. It partially does by mapping the one-of alternatives: 'small files' to the files array, 'ZIP archive_base64' to archive_base64, and 'allowed provider ZIP file reference' to the archive object. However, it doesn't clarify preview_id or accept_terms beyond their schema definitions, and the exact structure of files/archive is left entirely to the 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 states a specific purpose: 'Prepare replacement of an existing temporary static preview', clearly identifying an existing resource and a replacement action. This distinguishes it from create_preview (new preview) and delete_preview (removal), though the verb 'prepare replacement' is slightly indirect compared to a direct 'update' or 'replace'.

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 description gives concrete usage constraints: 'Supply exactly one of small files, ZIP archive_base64, or an allowed provider ZIP file reference' and explicitly notes 'No backend/build' and 'Requires explicit consent'. It also states the key precondition about the existing management key. It does not explicitly name sibling tools or when-not-to-use conditions, but the 'existing' qualifier and the approval-link flow imply the distinction.

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