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

Annotations only declare idempotentHint=true; the description goes well beyond that by disclosing beta gating with the `inboxes_not_enabled` error, that addresses are permanent and never recycled, and—critically—that this server never sends from an inbox so replies must go through a code-side POST. These are non-obvious behavioral constraints an agent cannot infer from the schema or annotations.

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?

Purpose and the shared-domain default are front-loaded, then idempotency, then the workflow handoff. Every clause carries information: the reply-path sentence in particular prevents the agent from hunting for a nonexistent send tool, so it earns its space rather than being padding.

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 zero-required-param creation tool with an output schema (so return values need not be described), the description covers the precondition, the default behavior, idempotency, follow-up tools, and the non-sending constraint. Nothing an agent needs to invoke this correctly 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?

Schema coverage is 100%, so the baseline is 3 and the schema already documents all four fields. The description still adds meaning beyond the schema by explaining the idempotency consequence of `clientId` in outcome terms ('returns the same inbox instead of making another') and reinforcing that omitting `domain` yields an immediately usable address.

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 ('Create an email inbox an agent can receive mail at') with the intended audience spelled out. It is immediately distinguishable from siblings like volanea_read_inbox, volanea_search_inbox, and volanea_wait_for_email, which are the consumption-side tools.

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?

Gives explicit routing: omit `domain` for the shared domain to get an immediately usable address, pass `clientId` to get idempotent re-calls, and then hand off to volanea_wait_for_email for receiving and volanea_read_inbox for reading. It also states the precondition (project must be in the private beta) and the resulting error code, which is exactly the when-not guidance an agent needs.

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