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

Annotations only declare the safety profile (not read-only, open-world, not idempotent, non-destructive); the description adds substantive behavior beyond that: a cold-outreach check runs, one-click unsubscribe is attached, each new recipient counts toward new-recipient limits, and refusals/rate_limited errors are terminal rather than retryable. It also states a PII exclusion list and treats message content as untrusted, which is context an agent cannot get from structured fields.

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 core action and its scope are front-loaded in the first sentence, and the remaining sentences each carry a distinct constraint (thread behavior, limits, PII, untrusted content). It is long and clause-dense, and the final prompt-injection paragraph reads as boilerplate appended to the send semantics, but no sentence is purely filler.

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 send tool with an output schema and full annotation coverage, the description covers what an agent needs before calling: domain/mailbox prerequisites, threading behavior, unsubscribe injection, limits, failure semantics, and content-safety rules. Nothing material about correct invocation 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 description coverage is 100%, so every parameter including mailbox, to, cc, subject, text/html and idempotency_key is already documented in the schema. The description adds no per-parameter detail such as address formats or how multiple recipients interact with the new-recipient limits, so baseline 3 applies.

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 description states a specific verb and resource ('Email someone first, from a mailbox on a verified domain of yours') and adds scope qualifiers that separate it from reply-style tools ('Hosted addresses can only reply', 'It starts a new thread'). It never names the sibling send_email or reply_to_mailbox_message, so differentiation is implied rather than explicit.

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 clear when-to-use context (first contact from a verified-domain mailbox, new thread) and strong when-not guidance: cold outreach is disallowed and a refusal or rate_limited error must not be worked around. Alternatives are not named, so an agent must infer that replies belong to the sibling reply tool.

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