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 covered; the closing 'All views are read-only' reinforces rather than adds. The per-view behavioral distinction (what each branch returns) is the real added value beyond structured data.

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: purpose first, option semantics second, safety note last. No filler, no repetition, and the front-loaded sentence carries the identity of the tool.

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 an output schema present, return values need not be described, and both parameters plus the modal branches are covered. Nothing essential to invoking this tool correctly is missing.

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 coverage is 100%, so the baseline is 3. The schema's own view descriptions are circular ('Select the detail operation explicitly'), so the description genuinely adds meaning by explaining what detail, markdown and versions actually yield; onlySnapshots remains schema-documented only.

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 (one document) and lookup key (UUID), and enumerates the three view modes, which is more than a restatement of the name. It does not, however, distinguish itself from sibling read-ish tools such as find_documents or get_document_index_status, so the agent must infer the boundary.

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 explicit selection criteria for each mode: detail = content and metadata, markdown = portable export, versions = saved revisions and snapshots. That is genuine when-to-use guidance for the tool's own branches, though it offers no guidance on when to prefer this tool over sibling readers.

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