opencode-mcp-bridge

Overview Schema Source Related Servers Discussions Admin

opencode_diff

Retrieve change metadata for a specific file tracked during a session. Provide a filepath to get details on modifications made, with an optional session ID to target a particular work session.

Instructions

Returns change metadata for a specific file tracked during the session.

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": {
      "filepath": "<filepath>"
    },
    "name": "opencode_diff"
  }
}

Input Schema

Name	Required	Description	Default
`filepath`	Yes	Relative or absolute path to the file.
`session_id`	No	Session ID (defaults to active session).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 4, 2026

TDQS

C2.6/5.0

Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It doesn't mention whether the file must exist, what happens if the file isn't tracked, whether this is read-only (safe), or what the return structure looks like. For a tool that doesn't reveal its output format, this is insufficient.

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?

A single concise sentence with zero waste. It's appropriately short and directly states the function. However, at this brevity it borders on under-specification rather than deliberate conciseness.

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

Completeness2/5

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

No annotations, no output schema, and 27 sibling tools create a complex context that this description does not address. For a tool that returns metadata (unclear return format), with no behavioral disclosures, and no usage contrast against similar checkpoint/list tools, the description is too thin.

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 description coverage is 100%, so the baseline is 3. The description adds nothing beyond the schema for the two parameters (filepath and session_id both self-explanatory in their enum-like descriptions). The description's mention of 'tracked during the session' hints at session context, which slightly complements the session_id parameter, but adds no new semantics.

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

Purpose3/5

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

The description says it returns 'change metadata' for a file, which is a specific verb+resource. However, 'change metadata' is somewhat ambiguous—it doesn't specify what kind of changes (diff content? timestamps? status flags?) or in what format. It's distinguishable from siblings like opencode_checkpoint, but the purpose could be sharper.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives. The description doesn't mention when a user would need change metadata, prerequisites (file must be tracked in session), or contrast with similar tools like opencode_checkpoint or opencode_list_checkpoints. With 27 siblings, this is a notable gap.

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