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

Annotations already declare idempotent/openWorld/no-destroy, and the description layers on genuine behavior: polling when 'preparing', persistence ('an unfinished preview survives reconnecting'), and that no app visit or list update follows. It notes internal-only fields (reviewId, itemRefs) but says nothing about what state the call itself creates, which matters given readOnlyHint=false.

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?

The lead sentence is well front-loaded, but the body is a dense run of eight clauses mixing workflow, rendering rules, and output constraints. With no output schema the rendering detail earns its place, yet the paragraph reads as stream-of-consciousness rather than prioritized guidance.

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?

No output schema exists, so the description correctly carries the return-value burden by enumerating what previewMarkdown contains (artwork, title/byline, note, description, labeled links) and what to omit. Timing and persistence are covered; what 'preparing' means and failure behavior are the main omissions.

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 100% with a single documented 'list' parameter, so the baseline is 3. The description mentions lists only incidentally ('later list update') and adds no syntax, format, or resolution detail for the 'list' argument beyond what the schema already states.

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 and resource ('fetch their enriched preview') and pins its position in the workflow ('after adding or importing picks'). An agent can tell it is the preview step rather than the staging or confirming step. It stops short of naming the adjacent siblings (pick_review_status, stage_picks) that an agent might confuse it with.

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 real timing context ('If preparing, wait briefly and call again') and a workflow cue ('Ask once if it looks good'), which is implied usage rather than explicit when/when-not. It never contrasts this tool with pick_review_status or review_import, so the agent must infer which preview/review tool applies.

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