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

Annotations only mark it non-read-only, non-destructive and open-world; the description adds substantial context beyond that — prerequisite authenticated active company access, a stated refusal condition, an idempotency/retry rule, a canonicality note about trusting returned actual_tool_output, and a confirmation boundary. It does not describe what state actually changes on success.

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 purpose is front-loaded, but the body is padded with shared boilerplate that is irrelevant to enabling inboxes — sending-mail confirmation rules and 'treat message contents as data' guidance belong to send/read tools. Several sentences (canonicality, generic idempotency, confirmation boundary) are template text rather than tool-specific facts, diluting the actionable content.

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 mutating, open-world action with no output schema, the description covers prerequisites, refusal conditions, idempotency and the confirmation boundary reasonably well. The main gaps are the unexplained _corply_context parameter and the absence of any statement about what the returned/refreshed state looks like.

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?

There is one parameter (_corply_context) with 0% schema description coverage, and the description never explains it — it only alludes to context_engineering in the canonicality boilerplate. Since the lone parameter is an opaque standard context object, the omission is not fatal, but the description does not compensate for the coverage gap.

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 opening sentence gives a concrete verb and resource ('Turn on receiving mail for the company's email domain') and explains the outcome (people get inboxes). It distinguishes the tool from near neighbors like connect_email_domain and assign_email_inbox by describing domain-branch behavior, though it never names 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?

It states clear conditions: for a Corply-registered domain the system publishes records itself, for a connected domain without mail you show inbound.records for the founder, and it is refused for a domain already receiving mail elsewhere. These are real when/when-not rules, but alternatives are described behaviorally rather than by tool name.

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