send_sms

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

Annotations already declare this is not read-only, is open-world, and is not idempotent. The description adds important context beyond annotations: it sends a real SMS, bills the workspace, supports MMS through mediaUrls, and changes requiredness of message depending on sendMode.

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 tight sentences with the core action, mode behavior, MMS/billing note, and sibling alternative front-loaded. Every sentence provides decision-relevant information without repetition.

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 an 11-parameter outbound messaging tool with no output schema, the description covers the essential selection and calling context: channel scope, send modes, billing, and the sibling tool for other channels. It does not describe the response or delivery confirmation, but the key operational details are present.

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 73%, so some parameters are already documented, but the description adds critical semantics for sendMode that the schema does not explain beyond the enum, and clarifies that message is optional in agent mode. It also maps mediaUrls to MMS behavior, though it does not cover parameters such as from, convoId, leadInfo, or campaignId.

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: it sends a REAL SMS from the agent's connected SMS number. It also distinguishes the tool from send_channel_message for WhatsApp, Messenger, and Instagram, so an agent can identify the correct channel-specific sender.

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?

It explicitly names the alternative for other messaging channels and explains the sendMode choices: direct sends the message as written, while agent lets the agent generate text and makes message optional. The default is stated, leaving little inference needed.

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