Skip to main content
Glama

submit_diff_review

Send a code-review job: the MCP server runs git diff inside repo_path and forwards the diff to the chosen provider. The diff content never appears in the LLM's output tokens, only the short tool call does.

Instructions

Send a code-review job: the MCP server runs git diff inside repo_path and forwards the diff to the chosen provider. The diff content never appears in the LLM's output tokens, only the short tool call does. When base is omitted, auto-detects: dirty working tree -> diff against HEAD; clean tree with main/master/origin-HEAD found -> ${detected}...HEAD; otherwise falls back to diff against HEAD. Pass base explicitly (e.g. "main", a tag, or a SHA) to force a ${base}...HEAD PR-style range. Optional prompt is prepended above the diff so reviewers can scope the review. Default capability is "review" - override if the provider advertises a different tag.

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": {
      "provider_npub": "<provider_npub>"
    },
    "name": "submit_diff_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoOptional base ref (branch, tag, SHA). When set, diffs ${base}...HEAD. When omitted, auto-detects working-tree vs main/master/origin-HEAD.
promptNoOptional instructions prepended above the diff (e.g. "focus on auth flow").
repo_pathNoPath to the git repo. Absolute or relative to the MCP server's working directory..
capabilityNoCapability tag advertised by the reviewer. Override if not "review".review
session_idNoConversation control. Omit for automatic session management (providers advertising context support get a conversation auto-started on first contact; an ongoing conversation triggers a continue/new/one-off question before anything is published). Pass "new" to force a fresh conversation, "none" to force a stateless one-off, or a session_id from a previous result to continue that conversation. The provider answers with the conversation context of prior exchanges under the same id.
kind_offsetNo
timeout_secsNo
provider_npubYes
allow_outside_cwdNoAllow reviewing a repo outside the MCP server working directory. Off by default - the diff is forwarded to the provider before payment and is invisible in the transcript, so the repo is confined to the working dir subtree unless this is set. Sensitive paths (secret keys, .env, SSH/keypair, ~/.elisym, /proc) are always refused.
max_price_lamportsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.60
    • addedInput schema / properties / max_price_lamports / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / max_price_lamports / minimum
      Added value: +-9007199254740991
  2. Addedv0.1.43
  3. Removedv0.1.42
  4. Changed1 schema field changedv0.1.38
    • addedInput schema / properties / allow_outside_cwd
      Added value: +{
      +  "default": false,
      +  "description": "Allow reviewing a repo outside the MCP server working directory. Off by default - the diff is forwarded to the provider before payment and is invisible in the transcript, so the repo is confined to the working dir subtree unless this is set. Sensitive paths (secret keys, .env, SSH/keypair, ~/.elisym, /proc) are always refused.",
      +  "type": "boolean"
      +}
  5. Addedv0.1.37
  6. Removedv0.1.36
  7. Addedv0.1.2

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does well on the unusual traits: the diff never enters output tokens, the diff is forwarded to the provider before payment, session handling is automatic, and paths outside the working directory need `allow_outside_cwd` while sensitive paths are always refused. However, it never says whether the call blocks until review completion, what it returns, or how `max_price_lamports` and cost estimation work, which is a real gap for a paid job tool.

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?

The definition is front-loaded with the core mechanism, then proceeds to detection fallbacks, explicit overrides, and the capability default. Each sentence carries information, although the auto-detect sentence is dense enough to be hard to parse in one pass. Minor tightening is possible, but nothing 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?

For a 10-parameter tool with no annotations and no output schema, the description covers behavior and the diff-scoping parameters well but leaves the agent without price, timeout, and result-shape information. `max_price_lamports` and `timeout_secs` remain unexplained despite being safety- and cost-relevant. Since no output schema exists, a short note on what comes back would have closed the gap.

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 sits at 60%, and the description adds meaningful context for `base` (auto-detection rules), `prompt` (prepended to scope the review), and `capability` (default review). But it is silent on four parameters that have no schema descriptions at all: `kind_offset`, `timeout_secs`, `max_price_lamports`, and `provider_npub`. Vague names like `kind_offset` especially need explanation that neither the schema nor the description provides.

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

Purpose5/5

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

The description names a specific action and resource: it sends a code-review job where the server runs `git diff` in repo_path and forwards the result to a chosen provider. That mechanism (diff capture plus provider selection) clearly separates it from the generic job-submission siblings, so an agent can tell what it does without reading the schema.

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

Usage Guidelines4/5

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

It gives concrete guidance for the key decision: omit `base` to auto-detect (dirty tree, main/master/origin-HEAD, HEAD fallback), or pass it explicitly to force a `${base}...HEAD` PR-style range, and it says to override `capability` only when the provider advertises a different tag. It stops short of stating when to pick this tool over the generic submit_and_pay_job sibling or what the prerequisites are (such as payment or an existing contact).

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