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

Annotations already declare non-readonly, idempotent, non-destructive and closed-world. Beyond that, the description adds real behavioral context: it clarifies what it does not touch (DNS, ownership, verification) and that sends still require domain verification, which meaningfully informs the agent's expectations for a mutation tool.

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 tight sentences, front-loaded with the core action and field list, followed by scope limits and the resource pointer. Every sentence carries information; nothing is padding, though the field list is slightly clipped in phrasing.

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, a nested loose payload, and 2 params, the description covers the mutation scope, the boundaries of effect, and verification prerequisites, plus a guide resource. It is nearly sufficient; only explicit when-to-use routing versus siblings is missing.

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?

The schema documents only the loose 'payload' object (50% coverage, additionalProperties true), so the description's explicit enumeration of domainId, expectedRevision, fromLocalPart, companyName and physicalAddress supplies semantics the schema does not. This is genuine added value over the structured fields.

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 (Update) and resource (the connected account's own-domain sender identity) and enumerates the payload fields it concerns, so an agent can distinguish it from generic email tools. It does not explicitly contrast itself with siblings like inspect_email_workspace or configure_email_tracking, but the scope is unambiguous.

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 useful boundary conditions ('Does not modify DNS, domain ownership or verification', 'All sends still require current domain verification') and points to a workflow guide, implying when it fits. However, it never states when to choose this over alternatives or what prerequisites trigger its use, leaving usage largely inferred.

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