Rams

Rams design review

review_files

Run a Rams design review over UI files (React, Vue, Svelte, CSS). Returns a 0-100 score (criticals cap it: one caps at 59, two at 49, three or more at 39), issues with severity, category, file:line, and concrete fixes. Call it whenever UI code has been written or changed: before committing, when the user asks how the design looks, or to check your own work after editing a component. Reviewing the handful of files you just touched is the normal case — it is cheap, and you do not need to ask permission first. Only a whole-codebase audit (dozens of files across many batches) is worth checking with the user, since it consumes the calling agent's context and a large share of their model allowance; prefer the highest-traffic screens in that case.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`files`	Yes	UI files to review (up to 20)
`context`	No	Short label for this review, e.g. the feature or branch name

Output Schema

TableJSON Schema

Name	Required	Description
`score`	Yes	0-100; confirmed criticals cap it — one at 59, two at 49, three or more at 39
`issues`	Yes
`summary`	Yes
`direction`	No	What the change is trying to be — judgment before findings
`reviewsUsed`	Yes
`reviewsLimit`	Yes	null = unlimited (Team overage applies instead)
`detectedCounts`	Yes

TDQS

A4.4/5.0

Behavior5/5

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

Beyond annotations, it discloses the critical scoring cap rule and cost/permission behavior, including that small reviews are cheap and need no permission while large audits consume context and model allowance. This is valuable behavioral context not present in annotations; no contradiction exists.

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?

Each sentence carries operational or behavioral value: behavior, scoring details, usage triggers, cost, and permission boundaries. It is compact and front-loaded with the core purpose and expected output.

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

Completeness5/5

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

The description covers the return shape, scoring edge cases, usage triggers, cost, and permission boundary, while the output schema handles the exact result structure. Nothing an agent needs to invoke it correctly is missing.

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?

The schema already documents both parameters at 100% coverage, so the baseline is 3. The description adds useful meaning by specifying supported file types (React, Vue, Svelte, CSS) and indicating large audits may require batching, although it does not expand on the optional context parameter.

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 clearly states the tool runs a Rams design review over UI files (React, Vue, Svelte, CSS) and summarizes the output (0-100 score, issues, fixes), which is specific and actionable. However, it never explicitly distinguishes itself from sibling tools like quick_review, so it falls short of full sibling differentiation.

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 gives explicit triggers ('before committing, when the user asks how the design looks, or to check your own work') and an explicit when-not ('Only a whole-codebase audit ... is worth checking with the user'). It does not name any alternative sibling tool, so the alternatives portion of the guidance is missing.

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

All Rams tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation3/5

The primary overlap is between quick_review and review_files, both triggered on the same UI-change events; they differ mainly in depth and cost, which could confuse an agent. usage and verify_fixes are clearly distinct. The detailed descriptions mitigate but don't eliminate the ambiguity.

Naming Consistency3/5

All names use snake_case, but surface structure varies: quick_review is adjective_noun, review_files and verify_fixes are verb_noun, and usage is a bare noun. The inconsistent verb placement (quick_review vs review_files) adds to confusion. Still readable and not chaotic.

Tool Count5/5

Four tools is an appropriate footprint for a design-review MCP server. Each serves a clear slot in the workflow—quick check, full review, quota lookup, and fix verification—without bloat.

Completeness4/5

The core design-review loop (review, fix, verify, check usage) is well covered. Minor gaps like listing past reviews or configuring rules would be nice but aren't essential to the primary purpose. The server achieves its stated goal with minimal dead ends.

Resources

Need Help?