Send a prompt to an AI session and wait for the AI response, enabling MCP clients to submit queries and retrieve model output over HTTP.
Send a prompt to a session and wait for the AI response.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| agent | No | ||
| format | No | ||
| system | No | ||
| modelID | No | ||
| noReply | No | ||
| variant | No | ||
| directory | No | Project directory to target. Optional; defaults to the server default project. | |
| sessionId | Yes | ||
| providerID | No |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose one genuinely useful behavioral trait beyond the schema: the call blocks until the AI reply arrives. However, it says nothing about error/timeout behavior, permission requirements, or what happens with noReply=true versus the default.
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?
A single well-formed sentence with the action front-loaded and no filler. It is efficient, though arguably terse for a 10-parameter tool, so it stops short of ideal.
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 10-parameter, annotation-free tool with no output schema and 90% undocumented parameters, one sentence is far too thin. An agent gets no sense of model/agent selection, reply content shape, or failure modes before invoking it.
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?
Only 1 of 10 parameters (directory) has any schema description, so coverage is 10% and the description adds no parameter meaning at all. Undocumented fields such as agent, modelID, providerID, variant, format, system, and noReply are left entirely to guesswork, which does not compensate for the schema gap.
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 verb (send) and resource (prompt to a session) plus the outcome (wait for the AI response). The waiting clause implicitly distinguishes it from the sibling opencode_message_send_async, but the sibling is never named, so the differentiation is left to inference.
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?
Usage is only implied: 'wait for the AI response' signals a blocking call versus the non-blocking opencode_message_send_async, but there is no explicit when-to-use/when-not-to-use statement, no mention of prerequisites (session must exist), and no guidance on choosing between the two send tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.