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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the safety profile is covered. The description adds two non-obvious facts not in the annotations: the From address is fixed to the agent's own address, and mail to outside addresses incurs a wallet charge. It stops short of delivery behavior, rate limits, or irreversibility (no unsend), which keeps it below 5.

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?

Two short sentences, zero filler, with the core action front-loaded and the cost caveat second. Nothing is repeated from the title or annotations.

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 7-parameter mutation with no output schema, the description covers purpose, sender identity and cost, which is the essential shape. It omits what the call returns (message id?), what happens on invalid/undeliverable recipients, and whether both body fields may be supplied — gaps that matter for an open-world side-effecting call.

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 57%: to, replyTo, htmlBody and textBody are documented, while cc, bcc and subject are bare. The description contributes one meaningful parameter fact — that no From/from address can be supplied because the sender is fixed — but says nothing about cc/bcc, the html-vs-text body relationship, or subject's requiredness. Baseline 3 fits given the partial schema coverage.

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 ("Sends an email") plus the scope of the sender identity ("from this agent's address"). It is clearly distinguishable from the read/manage siblings (mail_get, mail_list, mail_delete, mail_move) by the send verb, though it never names a sibling 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?

The billing sentence implies a when-to-care condition (external recipients cost money), which is useful decision context. However, there is no explicit when-to-use/when-not guidance, no mention of prerequisites (verified domain? mailbox must exist?), and no routing to alternatives — usage is only implied.

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