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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavior: paging in bounded base64 chunks, the requirement to reassemble all pages and verify SHA-256 before opening, and the 'this is not approval' caveat. It omits page-size limits and failure behavior, so not a 5.

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?

Three tight sentences, front-loaded with the core action, followed by the verification requirement and the approval caveat. No filler, though the SHA-256 reassembly instruction reads slightly like procedural advice rather than API semantics.

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, a nested revision object, and 0% schema coverage, the description is adequate on behavior but thin on the parameters an agent must supply. An agent knows roughly what the call does but not how to build itemId or the revision payload.

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 carries the full burden, yet it explains neither itemId nor the nested revision (outputJobId/payloadHash). It only loosely gestures at offset/maxBytes via 'bounded base64 pages' and at payloadHash via 'full-file SHA-256', leaving most parameters undefined.

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 (read) and resource (real bytes of a current produced review file) plus the delivery shape (bounded base64 pages). An agent can grasp the action precisely, though it does not name which sibling to prefer for adjacent tasks like output_download or inspect_original.

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 a usage context ('Review the actual document and layout before human confirmation') and an explicit exclusion ('This is not approval'), which frames when it applies. However it never names an alternative tool or a when-not condition, so routing against the ~120 siblings is left to inference.

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