agent_send

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

Annotations only flag non-read-only and non-destructive. The description adds a meaningful behavioral caveat that OpenCode 'accepted' only means transport queued, not completion. It also clarifies model/agent/reasoning are separate controls, useful for side-effect expectations. No contradiction with annotations.

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 sentences, front-loaded with the core action; no fluff. The second sentence is somewhat terse but still meaningful, and the OpenCode caveat 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 mutation tool with no output schema and no annotation safety context, the description omits return behavior, error/timeout semantics, and the meaning of mode/native session prerequisites. The OpenCode caveat helps but leaves other providers' acceptance semantics uncovered.

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 carries the burden. It names model, agent, and reasoning and groups them as separate controls, but leaves mode (send/steer), provider, nativeId, and text semantics unexplained. This is not enough for a 7-parameter tool.

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 clear verb and resource: 'Send a message to a provider native session.' The note that model, agent, and reasoning are separate controls helps distinguish it from set_model/set_reasoning siblings. However, it doesn't explicitly separate it from send_message or conversation_send, so not a 5.

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 implies its context ('provider native session') and gives provider-specific semantics for OpenCode. It does not state when to prefer agent_send over send_message/conversation_send or when not to use it, so an agent must infer routing from sibling names.

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