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

Annotations already declare readOnly/idempotent/no-destructive, so safety is covered. Beyond that the description discloses paginated base64 delivery, the requirement to verify a full SHA-256 after reassembly, and concrete failure modes (changed assignment, draft/expired original) — meaningful behavioral context.

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 tight sentences, front-loaded with the core action and paging model, then verification requirement, then failure modes. Every clause carries useful information with no padding.

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 read-only tool with no output schema, the description supplies the paging model, the mandatory verification step, and failure conditions, which is close to what an agent needs. The main gap is the semantics of the required assignmentRevision parameter.

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 burden. It implies offset/maxBytes paging ('bounded base64 pages') and hints at integrity checks, but does not explain the required assignmentRevision object (outputJobId + payloadHash) or how the hash relates to verification, leaving the required nested parameter under-specified.

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'), resource ('actual original bytes for a current client-file assignment'), and output shape ('bounded base64 pages'). It also contrasts against source excerpts ('never treat source excerpts as an original'), which helps distinguish it within the large original/source-reading sibling cluster.

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 a clear usage directive ('Only work on a copy') and a when-not via failure conditions ('Changed assignments, sources, draft or expired originals fail'), which tells the agent when this call is inapplicable. It stops short of naming alternative tools like read_source_original or read_original_page.

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