conversation_send

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

The description goes well beyond the minimal annotations by disclosing persistence-before-delivery, the receipt statuses (queued/rejected/delivery_unknown), idempotency semantics for retries, and the fact that replies require a separate send. This is exactly the kind of behavioral context an agent needs and is not present in the annotations or schema.

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?

Three dense sentences deliver high-value behavioral guidance without wasted words. The most important operational facts (persistence, receipt statuses, idempotency, reply behavior) are front-loaded and each sentence earns its place.

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 tool with 8 parameters, no output schema, and 0% schema description coverage, this description covers the core delivery semantics and retry safety well. However, it omits context around what the other parameters control (model, reasoning, replyTo) and never explicitly states that the tool sends a message. It is adequate but leaves meaningful gaps.

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 carries the burden of explaining parameters. It only meaningfully explains idempotencyKey, giving its purpose and examples like workId/handoffId. The other seven parameters—including required ones like conversationId, sender, recipient, and text—receive no semantic clarification beyond their names in the 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 strongly implies a send operation: "delivery," "receipt," "queued/rejected/delivery_unknown," and "Replies need another explicit send" all point to sending a message in a conversation. It is clear enough to infer the core action, but it never states the verb+resource directly (e.g., "Sends a message in a conversation") and does not differentiate itself from siblings like send_message or agent_send.

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 offers practical guidance: persist before delivery, use idempotencyKey for safe retries, and send again for replies. However, it does not explicitly say when to prefer this tool over alternatives such as send_message or agent_send, nor does it state exclusions or prerequisites. Usage context is implied rather than explicitly contrasted.

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