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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so 'without applying it' largely restates them. The genuinely additive content is the dependency signal — the text must be the exact output of run_content_subtask — and the claim that edits are 'bounded'. It says nothing about what happens on a stale revision/hash, what the preview returns, or what 'bounded' means numerically.

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 sentences, front-loaded with purpose before parameter routing, with no filler. The closing clause 'do not need a content-stage route' introduces undefined jargon that the reader must infer from earlier context, which costs a point but the text is otherwise tight.

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?

This is a complex tool — five parameters, a large discriminated operation union, and optimistic-concurrency fields — and the description addresses only the authoringMode branch. An agent still cannot tell which operations are valid for a given variant, why expectedRevision and expectedContentHash are required, or what failure looks like when they mismatch. An output schema exists, so return values need not be explained, but the input side is under-served relative to the tool's complexity.

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 carry parameter meaning, and it covers only part of one parameter: two of the three authoringMode enum values (current_turn_model is never mentioned) and none of the operation semantics. variantId, expectedRevision, expectedContentHash, and the entire 12-variant operations union (replace_text, edit_attachment, replace_metadata, set_auto_plug, etc.) get no explanation at all, leaving the highest-risk inputs undocumented.

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 first sentence names a specific verb and resource — 'Preview a bounded content variant edit without applying it' — which is unambiguous and clearly differentiates it from the other preview_* siblings that target ideas, schedules, media requests, and profile settings. It stops short of explicitly naming a sibling it is not, but the resource noun alone is distinctive enough for correct selection.

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?

It gives actionable routing guidance for the authoringMode choice: stage_model for AI-generated text produced by run_content_subtask, user_provided for exact user copy, and a stated exclusion that metadata and media-only edits need no content-stage route. It never contrasts this tool with other preview tools or states prerequisites such as the need for a prior subtask run, so it is context-rich but not a full when/when-not map.

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