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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: missing/stale/unsourced required answers yield no usable value, a working-copy value is not final file approval, and citations belong in the separate audit. These caveats are valuable, though the 'revision' semantics remain cryptic.

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 compact sentences, front-loaded with the core action and return contents. Each sentence conveys a distinct constraint, though the dense compound phrasing ('Reassemble this exact revision') reduces immediate clarity.

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 usefully signals the return contents (value plus sources, author, approval state), which partially covers the gap. But for a six-parameter, nested-object tool it leaves key mechanics unexplained — how pagination completes, and what expectedRevision must match — so an agent lacks enough to call it confidently.

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 only 17% and six parameters include a nested expectedRevision object whose fields are undocumented. The description only obliquely touches pagination ('next bounded Unicode page', implying offset/maxChars) and says nothing about expectedRevision/outputJobId/payloadHash or fieldId/documentId, so it fails to compensate for the coverage gap.

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?

Names a specific verb and resource (read a bounded Unicode page of one filling value) and states what is returned alongside it (sources, author, approval state), which distinguishes it from generic read siblings like read_produced_document. The jargon 'filling value' and 'reassemble this exact revision' obscures the domain slightly, and it does not explicitly contrast itself with read_filling_handoff.

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?

'Read the next bounded Unicode page' plus 'Reassemble this exact revision' implies the paginate-until-complete workflow, and the staleness/working-copy caveats hint at when the result is trustworthy. However there is no explicit guidance on when to use this tool versus sibling tools such as read_filling_handoff or read_produced_document, so usage is only implied.

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