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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing failure modes — unknown objects, missing required parts, and markup inboxes can't render are rejected — plus the default-restoring semantics of empty subject/preheader. It stops short of saying what state reset destroys or what a successful call returns.

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 front-loaded sentence with the writable fields listed before the validation caveat, so no sentence is wasted. The phrasing 'or reset: true' is slightly compressed and reads as schema leakage rather than prose.

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 destructive six-parameter mutation with no output schema, the definition covers inputs and rejection cases but omits what a successful call returns and whether partial updates are permitted (omitted fields untouched vs. cleared). Adjacent tools like preview_site_email, which a careful agent would want to know about, go unmentioned.

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 all six parameters are already documented, including the enum's pointer to list_site_emails and the 200-char limits. The description reinforces which fields are the writable surface and that reset is a boolean toggle, but adds no syntax or precedence detail (e.g. what happens if reset and source are sent together). Baseline 3 is appropriate.

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?

Names a specific verb (Save) and resource (site email) and enumerates the mutable surface: subject, preheader, Liquid source, or reset. An agent can distinguish it from get_site_email, preview_site_email and list_site_emails without opening a schema, though it doesn't name those siblings 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?

There is no when-to-use guidance: nothing says to call get_site_email or list_site_emails first, or when reset is preferable to supplying a new source. The only usage-adjacent content is a list of rejection conditions, which constrains the call rather than explaining when to make it.

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