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

The description discloses meaningful behavioral traits beyond the annotations: 'No backend/build,' 'Requires explicit consent,' 'returns an approval link, not a published URL,' and 'User must confirm in their browser.' This communicates the two-step approval flow and the fact that no published output is produced immediately. The annotations provide little behavioral detail, so the description carries that burden effectively.

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 compact and every clause earns its place. It front-loads the core action, then gives the input constraint, the no-backend caveat, and the critical approval-link behavior. No filler or repetition is present.

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 tool with no output schema and complex nested parameters, the description covers the essential operational context: one-of input modes, required consent, approval-link response, and user confirmation step. It does not elaborate on follow-up actions after approval or field-level requirements, but the input schema covers those details. The main gap is that it does not point to get_operation_status or get_preview_status for tracking the approval flow.

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 does explain the conceptual one-of relationship among files, archive_base64, and archive, and it ties 'explicit consent' to the required accept_terms field. However, it does not describe the nested structures within files or archive, leaving some parameter meaning to the schema property names alone. This is adequate but not complete.

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 opens with a specific verb and resource: 'Prepare a new temporary static preview.' It further distinguishes the tool from siblings by noting this is a new preview, adding 'No backend/build' and clarifying it returns an approval link rather than a published URL. This clearly separates it from delete_preview, update_preview, and the status tools.

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 clear context for when to invoke this tool: to create a new temporary static preview. It also provides concrete input-mode guidance with 'Supply exactly one of small files, ZIP archive_base64, or an allowed provider ZIP file reference.' However, it does not explicitly contrast this with alternatives or state when not to use it, so it stops short of a 5.

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