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

Annotations already declare readOnlyHint=true, but the description adds context beyond them: 'changes nothing and sends nothing' explicitly distinguishes it from send_test, and it discloses the required auth scope (settings:read). It also clarifies the save path (update_settings) so an agent understands persistence is not a side effect.

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?

Front-loaded with the read-only guarantee and the core action, then conditional behavior, then purpose. Dense but nearly every clause earns its place; the parenthetical scope note is slightly compressed but functional.

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, yet the description enumerates the return values (subject, body, sample used). With the save path and non-sending guarantee covered, an agent has everything needed to call and interpret this tool 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 coverage is 100%, so baseline is 3; the description adds behavioral meaning to subject/body by explaining that omitting them falls back to saved values while supplying them previews a draft. That goes beyond the schema's 'default: the saved one' wording but does not add format or validation detail.

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: 'Render a form's auto-reply against sample answers' and names the outputs (subject, body, sample used). It is clearly distinguishable from siblings like send_test (which sends) and preview_draft/preview_version (which preview sites/versions, not mail auto-replies).

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?

Explicit branching guidance: without subject/body it renders the saved version; with them it previews a draft before update_settings saves it. It also names the intended purpose ('show the user what the sender would receive') and implicitly routes saving to update_settings.

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