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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral trait beyond them: the call can return 'unchanged' when afterRevision/afterVersion still hold, implying a snapshot-diff/conditional-refresh semantic. It says nothing about latency, blocking/waiting, or the sensitivity of editorKey, so it lands at an adequate 3.

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?

A single compact sentence, front-loaded with the primary return behavior. The second clause is awkwardly worded ('or unchanged while afterRevision and afterVersion still hold'), which costs a point, but there is no filler.

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?

An output schema exists, so return values need not be described, and the description does cover the conditional unchanged case. However, for a 4-parameter, 2-required tool with 50% schema coverage and no usage framing against 27 sibling document tools, the definition leaves the agent guessing about when to choose this over the other context/read tools.

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 only 50%: afterVersion and afterRevision have no schema descriptions at all, and document/editorKey do. The description's clause about those two parameters still 'holding' hints that they act as cursor/version tokens for the unchanged-return condition, which is real added meaning, but it is ambiguous phrasing that never states they are cursors from a prior response.

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 states a specific verb and resource: 'Returns this editor's workspace snapshot.' That is clear enough to distinguish a read/snapshot tool from write siblings like document.apply_edits or document.commit. It does not name any sibling explicitly, so it stops short of a 5.

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?

There is no statement of when to call this versus alternatives such as document.get_context, document.read_context, or document.find. The trailing clause implies a polling/no-op condition but never frames it as usage guidance or an exclusion. An agent must infer the call context entirely.

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