send_message

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

No annotations are provided, so the description carries the full burden — and it delivers. It discloses immediacy ('delivers immediately'), irreversibility ('scripting cannot unsend it'), automatic transport selection (iMessage/SMS/RCS), and why the tool addresses a chat rather than a raw handle. This is precisely the behavioral context an agent needs before invoking an irreversible action.

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?

Well-structured with the critical IRREVERSIBLE warning front-loaded immediately after the one-line purpose. The compose_message alternative is mentioned twice, but each mention serves a distinct routing case. Slightly longer than strictly necessary, yet every sentence carries safety-relevant content, so the length is earned.

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 safety-critical, irreversible tool with zero annotations and zero schema descriptions, this is remarkably complete: it covers safety guardrails, when-to-use routing, transport behavior, parameter sourcing, and the confirm requirement. An output schema exists, so return values need not be documented. Nothing essential for correct invocation is missing.

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 description coverage is 0%, so the description must compensate — it does fully. chat_id is sourced from list_chats, body is defined as text, and confirm is documented as 'Must be True' with its safety purpose explained. Notably, the schema marks confirm as optional with default false, and the description corrects this dangerous ambiguity by stating the requirement explicitly.

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?

States a specific action ('Send a message to an existing conversation') with an unambiguous verb+resource pair. It distinguishes itself from sibling compose_message by explicitly scoping to existing conversations, and from the read-only siblings by naming the mutation it performs.

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?

Explicitly names compose_message as the alternative in two distinct routing conditions: when the user has not clearly asked for sending, and when starting a new conversation. Also instructs the agent to confirm recipient and wording with the user before calling, leaving no ambiguity about when this tool is appropriate.

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