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

Annotations already declare readOnlyHint=false, openWorldHint=true and non-idempotent, so the mutation profile is covered. The description adds non-obvious workflow context beyond that: an approval link is returned rather than a published URL, the user must confirm in the browser, and consent is mandatory. It still omits preview lifetime/expiry and any rate or size ceilings beyond 'small'.

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?

Four compact sentences, front-loaded with the core action, then constraints, then outcome. Every sentence carries information; only the final consent sentence slightly overlaps the earlier 'Requires explicit consent' clause.

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 consent-gated, non-publishing preview creation tool with no output schema, the description covers the essential workflow: what is created, the input constraint, the consent gate, and the fact that approval happens out of band in a browser. It does not point at get_preview_status or get_operation_status for follow-up, which is a minor omission.

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?

With 0% schema description coverage, the description carries the full burden, and it partially compensates: the mutual-exclusivity rule between files and archive_base64 is stated and 'explicit consent' maps to accept_terms. But it does not explain the per-file path/content/encoding fields, the nested file structure, or any size limits, leaving meaningful gaps.

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 verb and resource ('Prepare a new temporary static preview') and the qualifiers 'new' and 'temporary static' distinguish it from update_preview and delete_preview. It stops short of explicitly naming a sibling or contrasting its role, so it is clear but not maximally differentiated.

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?

'Supply exactly one of small files or ZIP archive_base64' and 'Requires explicit consent' give real calling context, and 'No backend/build' narrows the scope of what is acceptable. However, there is no explicit when-to-use vs when-not guidance relative to siblings like update_preview or get_preview_status; usage is implied rather than stated.

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