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

Adds real value beyond the readOnlyHint/idempotentHint annotations by disclosing what the preview contains: desktop and mobile inbox renderings for email, phone view plus segment count for SMS, and design checks. The 'changes nothing' statement reinforces the non-mutating trait concisely.

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 dense sentence plus a two-word safety statement. The rendering details are front-loaded and every clause (channels, views, data source, design checks) carries distinct information.

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 does the work of telling the agent what comes back — rendered views, segment counts, and design checks. Only gap is no indication of output format/structure, but for a preview tool this is close to sufficient.

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% and the owner_id description already explains 'real data instead of sample data', so the description's mention of sample vs real data is largely redundant. Baseline 3 is appropriate when the schema fully documents both parameters.

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?

Specific verb (preview/show) plus resource (saved email or SMS template) and the rendering modes (inbox view desktop/mobile, phone view, segment count). It distinguishes itself from retrieval siblings like spur_get_message_template by making clear it renders rather than returns raw template data, though no sibling is named 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?

The 'sample data or a real owner's data' clause gives clear context for when to use each mode, and 'changes nothing' signals this is a safe inspection step before sending. No explicit exclusions or named alternatives (e.g. preview_message_draft vs get_message_template) are given.

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