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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-inferable behavior: it does not scan, does not reset the preview clock, never returns 402 (i.e. triggers no payment), and claimable=false means the preview was deleted and the id is dead. That is real disclosure beyond the annotation block.

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?

Front-loaded with the purpose, then constraints, then the failure recovery path, then the alternative. Every sentence carries a distinct operator decision; nothing is filler, and the terse style ('never 402') is efficient for an agent audience.

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?

With no output schema, the description must carry return semantics, and it does partly by naming the claimable flag and framing the result as remaining time. It does not describe the shape/units of that remaining time, which is a minor residual gap for a read tool.

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 coverage is 100% for the single uploadId parameter, and its schema description already covers the 'part after /preview/' URL case. The description's 'uploadId is the UUID (a preview URL is OK)' largely restates that, so baseline 3 applies with no compensating added syntax.

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?

States a specific verb and resource — 'Read remaining preview time' — and immediately distinguishes itself from siblings by negation ('Does not scan, does not reset the clock') and by substitution ('Use this instead of inspect when you only need the clock'). An agent can route between preview_status, inspect, and scan without opening any schema.

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?

Gives explicit use-cases and exclusions, plus a full recovery procedure for the deleted-preview case naming the sibling tools in order (upload_url → PUT zip → inspect → claim) and two hard prohibitions ('Do not inspect or claim the old id', 'Do not pay'). This is a rare case of complete routing guidance.

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