Skip to main content
Glama

QualityKit fix (advise-only)

qualitykit.fix

Generates unified diffs and FileSpecs from technical findings or build contracts from page/query opportunities, letting the host agent apply safe fixes without writing to your repo.

Instructions

Technical findings → unified diffs/FileSpecs. page-* / gsc-query-* opportunityIds → buildContracts for the host agent (no invented page files). Never writes the repo. Use safeAutoOnly for low-risk technical fixes only.

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": {
      "projectRoot": "<projectRoot>"
    },
    "name": "qualitykit.fix"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiKeyNo
siteUrlNo
apiBaseUrlNo
findingIdsNoFinding IDs to generate technical/blog FileSpecs for
projectRootYesAbsolute path to the website repository root
safeAutoOnlyNoWhen true, only emit technical fixes marked fixSafety=auto (never page contracts)
opportunityIdsNoGrow/GSC opportunity ids (page-*, gsc-query-*, or finding ids). Pages/queries return buildContracts for the host agent; findings still map to diffs.
continueDespiteStaleProfileNoAllow new-page contracts when Site Profile brand/ICP/products are stale (user explicitly continues).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full disclosure burden, and it does deliver the most important trait: this is read/advise-only and 'Never writes the repo.' The '(no invented page files)' constraint is a useful guardrail. However, nothing is said about authentication (apiKey), what happens with a stale Site Profile beyond the flag name, or whether it reads/parses the repository — gaps that matter for an 8-parameter tool with zero annotation coverage.

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 content is front-loaded and extremely short: the primary mapping comes first, then the non-writing guarantee, then the flag rule — nothing is padding. The arrow/slash shorthand and unexplained internal terms ('FileSpecs', 'buildContracts') trade readability for compactness, keeping it just short of a 5.

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 an 8-parameter, no-annotation, no-output-schema tool, the description covers the core modes and the safety posture but leaves out the return shape beyond naming 'unified diffs/FileSpecs', and says nothing about auth or workflow position relative to audit/verify. It is enough to avoid misuse but not enough to invoke confidently in edge cases.

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 63%, and the description adds real meaning for safeAutoOnly (only fixSafety=auto technical fixes, never page contracts) and clarifies the opportunityId family (page-*, gsc-query-*). The required projectRoot plus apiKey/siteUrl/apiBaseUrl/continueDespiteStaleProfile are effectively schema-only, so a baseline 3 is appropriate rather than a higher score.

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 names a concrete input→output mapping (technical findings → unified diffs/FileSpecs; page-*/gsc-query-* opportunityIds → buildContracts) and explicitly states it never writes the repo, which separates it from an apply/patch tool. It loses a point because 'FileSpecs' and 'buildContracts' are undefined internal jargon, and the verb 'fix' in the name suggests mutation while the title says advise-only.

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?

Usage is only implied (you feed it findings or opportunityIds that presumably came from an audit) plus one flag-level rule: 'Use safeAutoOnly for low-risk technical fixes only.' There is no explicit when-not guidance and no routing to alternatives such as qualitykit.plan, seo.plan_changes, or qualitykit.verify, so an agent must infer the boundary itself.

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