suede-skills-mcp

Suede Code Grade

suede_code_grade

Read-onlyIdempotent

Generate a Suede A-F grading scaffold for diffs, PRs, branches, MCP servers, plugins, APIs, app surfaces, site changes, or release candidates to structure QA and review.

Instructions

Create a Suede A-F code grading scaffold for a diff, PR, branch, MCP server, plugin, API, app surface, public-site change, or release candidate.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "suede_code_grade"
  }
}

Input Schema

Name	Required	Description
`diff`	No	Optional pasted diff or change summary.
`repo`	No	Optional repository or project path.
`notes`	No	Optional constraints, verification notes, or risk context.
`intent`	No	Intended behavior or release goal.
`target`	No	Target repo, PR, branch, diff, file, or change to grade.
`context`	No	Optional pasted context or review notes.

Output Schema

Name	Required	Description	Default
`intent`	Yes
`target`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered and 'create a scaffold' is consistent with generating a returned artifact rather than persisting state. The description adds nothing about what the scaffold contains, how the A-F grading is derived, or depth/cost of the operation, so it only modestly exceeds the annotations.

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 front-loaded sentence with the verb and artifact first; the long target list is dense but each item adds scoping information. No filler or repetition.

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?

An output schema exists so return values need not be explained, and all parameters are documented. However, the central ambiguity — whether the tool actually performs grading or only emits a template/framework to fill in ('scaffold') — is unresolved, which matters for an agent deciding whether to rely on it for a verdict.

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% and all six parameters are optional with their own descriptions, so the baseline of 3 applies. The description's enumeration of gradable surfaces loosely maps to the 'target' parameter but gives no format, granularity, or precedence guidance across target/diff/repo/context/notes/intent.

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?

Uses a specific verb ('Create') and a named artifact ('Suede A-F code grading scaffold') and enumerates the input surfaces it applies to (diff, PR, branch, MCP server, plugin, API, app surface, public-site change, release candidate). This distinguishes it reasonably from grading siblings like suede_visibility_grade or suede_copy_check by scoping to code/release artifacts, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

The list of candidate targets implies when the tool applies, but there is no explicit when-to-use vs when-to-use-another rule and no prerequisites or exclusions. An agent must infer from the target enumeration whether, say, a live page audit should go here or to suede_live_page_audit.

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

Deploy Server