opencode_send_message

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

The description indicates a write operation ('Send') consistent with readOnlyHint=false, and adds return format details. However, it doesn't disclose potential errors, prerequisites (e.g., session must exist), or side effects beyond the basic send action. With minimal annotation coverage, this is a moderate disclosure.

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 succinct and front-loaded with the main purpose, followed by a usage note, return format, and example. Every sentence adds value without redundancy.

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 simple tool with two well-documented parameters and an output schema, the description covers the essential aspects: purpose, usage, return format, and an example. It lacks error handling details but is otherwise complete for an agent to invoke correctly.

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 100% with descriptions for both session_id and message. The description adds no extra parameter semantics beyond the example, which mirrors the schema. Baseline 3 applies since the schema fully documents parameters.

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 'Send a message to an existing opencode session' and 'continue a conversation with a running agent.' This provides a specific verb and resource, distinguishing it from siblings like opencode_get_messages (reading) and opencode_run_agent (starting a new agent).

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 phrase 'Use this to continue a conversation with a running agent' gives clear context for when to use this tool. It implies that it is not for starting new sessions or reading messages, though it doesn't explicitly name alternatives or exclusions.

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