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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is well covered. The description adds useful behavioral context beyond annotations: the trail is internal, field-to-original, and can be paged through entirely. It also cautions that this register is not silently included in buyer documents, which is valuable nuance. It does not mention permission requirements, but the read-only annotations lower the burden.

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 compact sentences, front-loaded with the main purpose and followed by the paging behavior and one key caveat. Every clause adds information, with no filler or repetition.

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?

Despite having no output schema, the description names what the trail contains (value hashes, sources, authors, review receipts) and states pagination. The nested revision object is not fully explained, but the field names and required structure in the schema are reasonably self-evident. A stronger definition would explicitly state that itemId identifies the produced file and how revision scopes the audit trail.

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, but it does not explain what itemId, revision, outputJobId, payloadHash, offset, or maxFields mean. 'Page through all records' weakly hints at offset/maxFields, and the schema's pattern constraints give some clues. Yet the core revision identification mechanism (outputJobId plus payloadHash) is left entirely to inference.

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 uses a specific verb ('Read') and a clearly defined resource ('internal field-to-original audit trail for one current produced file'). It further enumerates the content ('approved value hashes, sources, authors and review receipts') and distinguishes this tool from buyer-facing documents, making it unmistakable among the many read_* siblings.

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?

The description implies its use case: when one needs the internal audit trail for a produced file, especially field-level provenance. It adds that this register is 'not silently included in buyer documents,' which clarifies what it is not. However, it does not name alternative tools, state exclusions, or explain when another read tool would be more appropriate.

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