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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description still adds real value beyond them: no file is persisted or rendered, the operation costs nothing, and the returned HTML must be treated as untrusted data - a security-relevant disclosure the annotations do not carry.

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 short sentences, each earning its place: the core action, the no-side-effect guarantee, and the safety warning, with the most important framing front-loaded. 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?

For a preview tool the description does cover the key output (returned HTML) and the side-effect profile, which compensates for the absent output schema. However, with four undocumented parameters at 0% schema coverage and no guidance on data/schema format, an agent still lacks enough to call 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 0% for four parameters, two of them required, plus a nested object, so the description must compensate and largely does not. Only 'template source' and 'sample data' loosely gesture at source and data; schema, brand_kit_id, and the data object's shape are entirely unexplained.

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 names a concrete verb and resource ('expand template source with sample data') and explicitly contrasts the outcome with rendering or saving, which separates it from siblings like render and save_template. It stops short of naming those siblings directly, so it is clear but not maximally differentiated.

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?

'for free' and 'does not save or render a file' imply the intended use case - cheap iteration on a template before committing to render/save - but the description never states when to choose this over adapt_template or render, nor any prerequisites. Usage is implied rather than guided.

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