Skip to main content
Glama

system_design_review

Review system design proposals and constraints with parallel LLM reviewers. Provide proposal text or file paths for context, plus explicit constraints and background.

Instructions

Review a system design proposal and constraints using two LLM reviewers in parallel.

At least one of proposal or paths must be provided.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
proposalNoThe system design document to review. Must be at least 10 characters (and is ignored when `paths` is also provided). Required unless `paths` is provided (both can also be provided together).
pathsNoFile paths to existing implementation files that provide context for the review. Pass either: a list of paths (e.g. ['src/main.py', 'src/utils.py']), a newline-separated string of paths, or a JSON array string. Paths are relative to the current working directory; absolute paths also work. Files are read automatically from disk. Required unless `proposal` is provided (both can also be provided together).
constraintsNoExplicit constraints the design must satisfy (e.g., non-functional requirements, tech stack restrictions, performance targets). Max 10,000 characters.
contextNoBackground information to help the reviewer understand the design context (e.g., business goals, prior architectural decisions, known issues, scope). Max 10,000 characters.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior3/5

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

No annotations are provided, so the description must carry the burden. It discloses the use of two parallel reviewers, which is a behavioral trait. It does not explicitly state that the tool is read-only or non-destructive, but the context of a review implies that.

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 two sentences, front-loaded with the core purpose, and contains no fluff. Every word provides value.

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 4 parameters, an output schema exists, and a sibling tool, the description is fairly complete. It explains the parallel review mechanism and the requirement for input. Minor gap: no guidance on when to use this versus 'code_review'.

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 100%, so baseline is 3. The description adds minimal parameter information beyond the schema, only reiterating the condition for 'proposal' and 'paths'. The schema descriptions themselves are thorough.

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 verb 'review' and the resource 'system design proposal and constraints', with a distinctive behavioral detail 'using two LLM reviewers in parallel'. It implicitly differentiates from sibling 'code_review' by focusing on system design.

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 the prerequisite that at least one of 'proposal' or 'paths' must be provided. However, it does not provide guidance on when to use this tool versus the sibling 'code_review', though the tool name suggests the domain.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Shelpuk-AI-Technology-Consulting/lad_mcp_server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server