opencode-bridge

opencode_result

Fetches a task's output from the bridge with failure kind and advice, and limits large results using head or tail.

Instructions

Output of a task started by this bridge, with the failure kind and advice when it failed (rate_limit, quota, context_length, output_limit, overloaded, auth, model, agent, invalid_request, network, timeout, spawn, exit). Large outputs are cut to the last 60000 characters unless head / tail is given.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "opencode_result"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`head`	No	only the first N characters
`tail`	No	only the last N characters

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.0Nov 12, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden and does add real value: a concrete taxonomy of failure kinds and the 60,000-character truncation default are genuine behavioral disclosures. It omits, however, whether the call blocks until the task finishes, what happens for still-running tasks, or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Everything sits in one dense paragraph with the core purpose front-loaded and the failure list and truncation rule following logically. The long parenthetical enumeration of failure kinds is bulky but each term is informative, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema or annotations, the description does a reasonable job describing the return payload (output text plus failure kind and advice) and the truncation rule. It leaves open how the result relates to task lifecycle state — a meaningful gap for a polling-style retrieval tool with three parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, with head and tail already documented as first/last N characters. The description still contributes new meaning by stating that truncation to the last 60,000 characters is the default and that head/tail override it — an interaction the schema does not express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource — the output of a task started by this bridge — and adds that it carries failure kind and advice. It is clear about what is retrieved, but it never explicitly contrasts itself with close siblings such as opencode_session_output or opencode_status, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'started by this bridge' implies a prerequisite (a prior start call) but gives no explicit when-to-use or when-not guidance. Nothing tells the agent how this differs from polling opencode_status or reading via opencode_session_output, and no mention of whether it waits for completion or must be polled.

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

Deploy Server