Skip to main content
Glama
antonbabenko

Deliberation

by antonbabenko
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

code-reviewer

Read-only

Reviews code diffs or files for bugs, security holes, and maintainability before merging, not style nitpicks. Sends them to configured provider panel and returns structured findings.

Instructions

Senior engineer doing code review for bugs, security holes, and maintainability - not style nitpicks. Use to review a diff or file before merging. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
filesNoOptional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
expertNoOptional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
promptYesThe question or task for the provider(s)/expert.
reasoningEffortNoReasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.
developerInstructionsNoOptional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv3.8.1
    • addedInput schema / properties / cwd / description
      Added value: +"Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory."
    • addedInput schema / properties / developerInstructions / description
      Added value: +"Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`."
    • addedInput schema / properties / expert / description
      Added value: +"Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored."
    • addedInput schema / properties / files / description
      Added value: +"Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url."
    • addedInput schema / properties / files / items / properties / dir / description
      Added value: +"Directory to attach; expanded recursively by providers that support it."
    • addedInput schema / properties / files / items / properties / file_id / description
      Added value: +"Id of a file already uploaded to the provider (e.g. Grok Files API)."
    • addedInput schema / properties / files / items / properties / file_url / description
      Added value: +"Public URL for the provider to fetch."
    • addedInput schema / properties / files / items / properties / mode / description
      Added value: +"Delivery: auto (size-based), inline (embed as text), or upload (provider Files API)."
    • addedInput schema / properties / files / items / properties / path / description
      Added value: +"Path to a single file to attach (resolved against cwd)."
    • addedInput schema / properties / prompt / description
      Added value: +"The question or task for the provider(s)/expert."
    • addedInput schema / properties / reasoningEffort / description
      Added value: +"Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds beyond that by revealing the tool fans out to external providers (each needing keys/CLI and subject to rate limits), returns a text-wrapped JSON envelope with results[], and operates in an advisory persona. This informs the agent about dependencies and output format.

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

Conciseness5/5

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

The description is concise at three sentences, each serving a distinct purpose: stating the persona and scope, specifying when to use, and explaining the behavior and output. It is front-loaded and contains no redundant information.

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

Completeness4/5

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

Given the moderate complexity (6 parameters, no output schema), the description covers all essential aspects: purpose, usage, behavior, and output format (JSON envelope with results[]). It does not detail error handling or edge cases, but the annotations and schema fill remaining gaps, making it sufficiently 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.

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that on a named expert tool like this, the tool's own persona wins over the 'expert' parameter and that 'developerInstructions' overrides the built-in persona. This clarifies parameter behavior beyond the schema's field descriptions.

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 clearly states the tool performs code review focusing on bugs, security holes, and maintainability, distinguishing it from style nitpicks. It specifies the action (reviewing a diff or file before merging) and the resource (code), making the purpose immediately understandable.

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?

The description explicitly states when to use the tool: 'to review a diff or file before merging.' It also clarifies what not to do ('not style nitpicks'). However, it does not mention when to use alternative sibling tools like security-analyst or architect, missing an opportunity to guide the agent on tool selection.

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

Deploy Server

Other Tools