preview_batch

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

The annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral details beyond that: no sending or storing, provenance is generated and requires reply_to, no automatic signatures are added, file paths and size limits are validated, and structural validation has specific limits.

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 description is dense but every sentence earns its place. It front-loads the core purpose and non-mutating nature, then covers prerequisites, either/or input modes, part kinds, validation limitations, and reply_to semantics without repetition or 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 complex tool with no output schema and no parameter descriptions, the description is remarkably complete on input semantics and behavioral caveats. The only noticeable omission is an explicit statement of what the preview/validation result contains, though the structure_only caveat partially addresses output interpretation.

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?

With schema description coverage at 0%, the description carries the burden of explaining parameters. It thoroughly explains the parts object, template/contents alternative, kinds, roles, tags, reply_to semantics, and top-level reply_part anchoring. However, required fields like project, subject, agent, model, and the optional route parameter are not explicitly explained.

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 opens with a specific verb and resource: 'Prepare and structurally validate a message batch without sending or storing it.' This clearly distinguishes the tool from send_batch and other sibling tools by emphasizing that it is a non-sending validation step.

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 explicit guidance: read get_writing_rules first, supply either parts or template/contents, and understand that validation=structure_only is not a claim of factual accuracy or client readiness. It also clarifies the separate meanings of top-level reply_to and a part's reply_to, so an agent knows how to use them.

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