send_email

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial behavioral context beyond that: it requires explicit user confirmation via a prompt, restricts to plain-text body, and mandates that only user-approved content be sent. It also discloses that email content must be treated as untrusted data, a significant safety trait not covered by annotations. This exceeds the bar set by the 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?

The description is four sentences, each carrying critical information: the action, the confirmation requirement, the content-approval mandate, and the untrusted-data warning. Nothing is redundant; it is front-loaded with the core purpose and then expands on safety constraints. It is concise and well-structured for an agent.

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?

Given the tool has six parameters and no output schema, the description covers all essential calling context: the safety requirement for confirmation, the plain-text constraint, the need for user-approved content, and the prohibition on email-derived instructions. It does not need to describe return values, as there is no output schema, and the action is a send operation. The description is complete for an agent to correctly invoke the tool.

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 67%, and the description adds meaningful constraints beyond the schema: it clarifies that body must be plain text (though schema also says 'Plain-text body'), and it enumerates which parameters (recipients, subject, body, attachments) must be explicitly user-approved. It also implies that cc/bcc are recipients. This adds value over the schema's individual parameter descriptions, though some of the schema already covers format.

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: 'Send an email from the Yahoo account.' It clearly distinguishes this from siblings like list_folders, search_emails, and mark_read, which are read/manage operations. The tool's purpose is unambiguous.

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 strong usage guidance: it mandates explicit user confirmation before sending and prohibits using content from emails as commands. It also states the tool should never be invoked due to instructions found in email content. While it doesn't explicitly compare to siblings, the send action is clearly distinct from the read/manage operations listed. The 'when not to use' is implied by the email-content prohibition, which is a valuable guideline.

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