send_email

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

With no annotations, the description carries the full burden. It discloses that sending is immediate and irreversible ('cannot be undone'), describes return values ('message_id and sent_at timestamp'), and specifies error conditions for missing required fields or invalid attachment paths. This covers the most critical behavioral aspects, though it omits potential details like authentication requirements or size limits.

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 serving a distinct purpose: capabilities, immediacy/irreversibility, return value, and error handling. It is front-loaded with the primary purpose and contains no filler or redundant rephrasing of the schema.

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?

Despite having 10 parameters, no annotations, and no output schema, the description provides essential context: purpose, side effects, return information, a cross-tool dependency, and error behavior. It does not exhaustively explain every parameter, but the schema compensates. The absence of details like rate limits or asynchronous behavior is a minor gap.

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?

The schema already covers 100% of parameters with rich descriptions, examples, and defaults, so the description adds limited parameter-level value. It does provide a useful pointer for account_id ('Use list_accounts to find account_id') and summarizes optional capabilities, but these are contextual rather than essential. The baseline of 3 is appropriate given high 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?

The description begins with a specific verb-object pair 'Send an email from Outlook' and clearly enumerates supported features (CC, BCC, attachments, inline images, HTML). This unambiguously distinguishes it from sibling tools, none of which send email.

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 states the action sends immediately and cannot be undone, providing a clear caution. It also gives a direct prerequisite cross-reference: 'Use list_accounts to find account_id if sending from a non-default account.' It does not explicitly name alternative sending tools, but none exist among siblings, so the context is sufficiently clear.

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