acme-mailer.send_email

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

Annotations already classify the tool as destructive (destructiveHint: true) and non-idempotent, which aligns with sending an email, so there is no contradiction. But the description adds zero behavioral context beyond the action itself — no mention that delivery is irreversible, external, or side-effecting. With annotations covering the safety profile, some added context was expected and none was provided.

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 description is a single seven-word sentence with the action front-loaded and no filler. Every word earns its place, and it is appropriately sized for a one-parameter tool. Nothing could be removed without losing the verb-object clarity.

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 single-parameter tool with annotations and an output schema, an agent can likely invoke it correctly by passing `to`. However, the description is a bare minimum — it never explains what the email contains (subject, body, sender), whether the send is an actual external delivery or a simulation, or any delivery semantics, which matters given the destructive hint. Adequate but with clear gaps.

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% — the schema already describes `to` as 'Recipient email address.' The description's 'to a recipient' adds no parameter-level meaning beyond the schema, so the baseline 3 for high coverage applies. Notably, the schema marks zero required parameters, meaning an email without a recipient is technically permitted; the description does not clarify this oddity.

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 'Send an email to a recipient' states a specific verb (send), resource (email), and target (recipient), so an agent understands the core action immediately. No sibling tool is email-related, so there is no confusion. However, it stops just short of a 5 because it essentially restates the tool name in sentence form without adding scoping detail.

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 description provides no guidance on when to invoke this tool versus alternatives, no exclusions, and no prerequisites. While none of the 40 siblings overlap in domain, making mis-selection unlikely, the description itself earns no credit for this. This matches the rubric's 'no guidance' level.

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