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

Annotations already mark it read-only, idempotent, and non-destructive, but the description adds the essential behavioral contract: results are paginated base64 chunks, all pages must be reassembled, and the full-file SHA-256 must be verified before use. This is materially beyond the structured metadata and shapes how the agent must invoke and validate the call.

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?

Two tight sentences front-load the core purpose and verification requirement, then add the crucial 'not approval' caveat. There is no filler or repetition of schema details.

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 4-parameter tool with a nested revision object and no output schema, the description covers the critical protocol (page reassembly and hash verification) and the non-approval context. It stops short of describing the exact page response shape or revision semantics, but the agent has enough to call and validate it correctly.

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 connect payloadHash to the required full-file SHA-256 verification and pagination language ('pages') implies the offset/maxBytes parameters, but it never explains itemId or the revision.outputJobId structure. This is partial compensation, not full.

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 action–verb ('Read') and a precise object ('real bytes of a current produced review file'), then specifies the return mechanism ('bounded base64 pages'). It also draws a clear line against approval actions, which separates it from the many confirm/approve siblings without needing their schemas.

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 states the intended workflow: reassemble all pages and verify SHA-256 before relying on the content, and explicitly says 'This is not approval' and 'Review the actual document... before human confirmation.' It gives clear context and an exclusion, though it does not name a specific sibling as the alternative to use.

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