Skip to main content
Glama
Sign In

WerkCV – Dutch CV check

by nl.werkcv
OverviewDiscussionsAdmin

Check a CV (Dutch conventions)

check_cv
Read-onlyIdempotent

Grade a CV (cv, curriculum vitae, résumé) for the Dutch job market: 0-100 score plus a 1-10 grade, the three fixes to make first with the exact lines they refer to, and ATS readability. Use when the user asks 'is my CV good', 'check my CV', 'beoordeel mijn cv' or pastes a CV. Free, no AI, nothing stored. Remove BSN, ID and bank numbers first. The result includes nextStep, a suggested follow-up (usually open_in_editor).

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": {
      "cv_text": "<cv_text>"
    },
    "name": "check_cv"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoLanguage of the CV and the answer. Detected from the text when omitted.
cv_textYesThe full text of the CV (200-25,000 characters). Remove BSN, ID and bank numbers first.

Output Schema

NameRequiredDescriptionDefault
bandYes
metaYes
scoreYes
statsYes
grade10Yesscore / 10, one decimal, floor 1. The MCP grade; the website's CV check uses its own scale and can differ.
summaryYesOne sentence the agent can repeat as-is.
nextStepYes
topFixesYes
bandLabelYes
categoriesYes
limitationsYes
sectionsFoundYes
criticalIssuesYes
canOpenInEditorYes
otherFixesCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "band": {
+      "enum": [
+        "sterk",
+        "goed",
+        "in_ontwikkeling",
+        "zwak"
+      ],
+      "type": "string"
+    },
+    "bandLabel": {
+      "type": "string"
+    },
+    "canOpenInEditor": {
+      "type": "boolean"
+    },
+    "categories": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "id": {
+            "enum": [
+              "content",
+              "ats",
+              "basics",
+              "dutch_conventions"
+            ],
+            "type": "string"
+          },
+          "label": {
+            "type": "string"
+          },
+          "score": {
+            "maximum": 100,
+            "minimum": 0,
+            "type": "integer"
+          },
+          "weight": {
+            "maximum": 1,
+            "minimum": 0,
+            "type": "number"
+          }
+        },
+        "required": [
+          "id",
+          "label",
+          "score",
+          "weight"
+        ],
+        "type": "object"
+      },
+      "maxItems": 4,
+      "minItems": 4,
+      "type": "array"
+    },
+    "criticalIssues": {
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "grade10": {
+      "description": "score / 10, one decimal, floor 1. The MCP grade; the website's CV check uses its own scale and can differ.",
+      "maximum": 10,
+      "minimum": 1,
+      "type": "number"
+    },
+    "limitations": {
+      "type": "string"
+    },
+    "meta": {
+      "additionalProperties": false,
+      "properties": {
+        "locale": {
+          "enum": [
+            "nl",
+            "en"
+          ],
+          "type": "string"
+        },
+        "schemaVersion": {
+          "const": "2.0.0",
+          "type": "string"
+        },
+        "scoringVersion": {
+          "type": "string"
+        },
+        "tool": {
+          "enum": [
+            "check_cv",
+            "match_vacancy",
+            "open_in_editor"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "schemaVersion",
+        "scoringVersion",
+        "locale"
+      ],
+      "type": "object"
+    },
+    "nextStep": {
+      "additionalProperties": false,
+      "properties": {
+        "action": {
+          "enum": [
+            "open_in_editor",
+            "match_vacancy",
+            "none"
+          ],
+          "type": "string"
+        },
+        "reason": {
+          "type": "string"
+        },
+        "suggestedUserPrompt": {
+          "description": "A short line the agent can say to the user, in the CV's language.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "action",
+        "reason",
+        "suggestedUserPrompt"
+      ],
+      "type": "object"
+    },
+    "otherFixesCount": {
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "score": {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "sectionsFound": {
+      "items": {
+        "enum": [
+          "contact",
+          "profile",
+          "experience",
+          "education",
+          "skills",
+          "languages",
+          "certificates",
+          "hobbies",
+          "general"
+        ],
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "stats": {
+      "additionalProperties": false,
+      "properties": {
+        "clichesFound": {
+          "description": "Exact phrases like 'teamplayer', 'nieuwe uitdaging'",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "experienceBulletCount": {
+          "maximum": 9007199254740991,
+          "minimum": -9007199254740991,
+          "type": "integer"
+        },
+        "profileWordCount": {
+          "anyOf": [
+            {
+              "maximum": 9007199254740991,
+              "minimum": -9007199254740991,
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "quantifiedBulletCount": {
+          "maximum": 9007199254740991,
+          "minimum": -9007199254740991,
+          "type": "integer"
+        },
+        "weakBulletOpeners": {
+          "description": "Exact bullet openers like 'Verantwoordelijk voor'",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "wordCount": {
+          "maximum": 9007199254740991,
+          "minimum": -9007199254740991,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "wordCount",
+        "profileWordCount",
+        "experienceBulletCount",
+        "quantifiedBulletCount",
+        "weakBulletOpeners",
+        "clichesFound"
+      ],
+      "type": "object"
+    },
+    "summary": {
+      "description": "One sentence the agent can repeat as-is.",
+      "type": "string"
+    },
+    "topFixes": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "example": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional rewritten line in the CV's language. Must not invent facts; use [X] for numbers the user must fill in."
+          },
+          "fix": {
+            "description": "One sentence: what to change.",
+            "type": "string"
+          },
+          "id": {
+            "description": "Stable machine id, e.g. 'quantified_achievement'",
+            "type": "string"
+          },
+          "problem": {
+            "description": "One sentence: what is wrong, with the measured value where there is one.",
+            "type": "string"
+          },
+          "quote": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Exact text copied from the CV that this fix is about. Null when the problem is something missing."
+          },
+          "section": {
+            "enum": [
+              "contact",
+              "profile",
+              "experience",
+              "education",
+              "skills",
+              "languages",
+              "certificates",
+              "hobbies",
+              "general"
+            ],
+            "type": "string"
+          },
+          "severity": {
+            "enum": [
+              "critical",
+              "high",
+              "medium",
+              "low"
+            ],
+            "type": "string"
+          },
+          "where": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Human location, e.g. 'Werkervaring > Marketing Coördinator, bullet 1'. Null for CV-wide issues."
+          }
+        },
+        "required": [
+          "id",
+          "severity",
+          "section",
+          "where",
+          "quote",
+          "problem",
+          "fix",
+          "example"
+        ],
+        "type": "object"
+      },
+      "maxItems": 3,
+      "type": "array"
+    }
+  },
+  "required": [
+    "score",
+    "grade10",
+    "band",
+    "bandLabel",
+    "summary",
+    "categories",
+    "stats",
+    "topFixes",
+    "otherFixesCount",
+    "criticalIssues",
+    "sectionsFound",
+    "canOpenInEditor",
+    "nextStep",
+    "limitations",
+    "meta"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds non-obvious context: 'Free, no AI, nothing stored' and the prereq 'Remove BSN, ID and bank numbers first', which is real behavioral guidance an agent would not otherwise have. It also foreshadows the nextStep/open_in_editor follow-up.

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?

Front-loaded with purpose, then triggers, then caveats and follow-up; every clause carries information. The trigger-phrase enumeration is slightly padded but directly supports tool selection, so it earns its space.

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?

With an output schema present, the description needn't enumerate return fields, yet it still previews the key ones (score, grade, three fixes, ATS) and flags nextStep. Annotations cover safety and the schema covers parameters, leaving no material gap for correct invocation.

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%, so both cv_text (200-25,000 chars) and the locale enum are already fully documented in the schema. The description's mention of Dutch-market grading lightly implies locale behavior and repeats the PII-removal warning, but adds no format/syntax detail beyond the schema. Baseline 3 applies.

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?

States a specific verb (grade) plus resource (CV) with concrete outputs: a 0-100 score, a 1-10 grade, three prioritized fixes with referenced lines, and ATS readability. The Dutch-market scope and the synonym list (cv, curriculum vitae, résumé) make it clearly distinguishable from match_vacancy and open_in_editor.

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?

Gives explicit trigger conditions, including literal user phrasings ('is my CV good', 'beoordeel mijn cv') and the paste-a-CV case, which is genuinely useful for routing. It stops short of stating when NOT to use it (e.g. use match_vacancy to compare against a job posting), so the alternative selection is only implied.

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

All WerkCV – Dutch CV check toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources