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

Annotations already declare readOnlyHint/idempotent/destructive=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it reveals refused_at_send names a failing content rule and enumerates exactly what gets rendered, which helps an agent interpret output.

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?

One dense sentence, front-loaded with the core purpose and the campaign_id distinction; the long parenthetical list of rendered pieces is heavy but earns its place by telling the agent what the preview contains.

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 compensates by naming the returned fields (subject, body, refused_at_send). Combined with the parameter branching for campaign_id/lane, an agent has enough to invoke and interpret it correctly.

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%, so the schema carries the parameter documentation. The description adds only a little nuance on campaign_id omission (autopilot default sequence) that the schema already gestures at, so the baseline 3 applies.

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 (preview/render) and resource (one step's email to one site), and names the rendered components. It is distinguishable from sibling previews like get_quick_scan_preview or check_draft, though it never routes against them explicitly.

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 real conditional context: pass campaign_id for a website campaign, omit it for an autopilot lane. However it never says when to use this tool versus alternatives (check_draft, get_thread), and offers no exclusions or prerequisites.

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