send_message

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It thoroughly documents critical behavioral traits: the limitation to existing conversations, lack of delivery confirmation, dependency on Messages.app running, and Automation permission requirement. This goes beyond what the input schema provides and addresses potential failure modes.

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 well-structured with clear sections (purpose, limitations, args, returns) and front-loads the core functionality. While comprehensive, it could be slightly more concise by integrating the 'Args' and 'Returns' sections more seamlessly, but every sentence adds value.

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's complexity (sending messages with dependencies and limitations), no annotations, and an output schema that documents return values, the description is complete. It covers purpose, usage constraints, parameters, and behavioral expectations, leaving no significant gaps for the agent.

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?

With 0% schema description coverage, the description fully compensates by explaining all three parameters: 'recipient' (phone number or email address), 'message' (text to send), and 'service' (iMessage or SMS with default). It adds meaningful context about parameter usage that isn't in the bare schema.

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 clearly states the tool's purpose with specific verb ('Send a message') and resource ('to an existing conversation via AppleScript'), distinguishing it from sibling tools like 'list_conversations' or 'get_conversation_messages' which are read-only. It specifies the exact mechanism (AppleScript) and target (existing conversations).

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 explicit usage guidelines in the 'IMPORTANT LIMITATIONS' section, detailing when to use (for existing conversations) and when not to use (no delivery confirmation, requires Messages.app running and Automation permission). It distinguishes this tool from alternatives by specifying it's for sending messages, not retrieving or managing them like sibling tools.

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