Civify

Parse Resume Document

civify_parse_cv

Parse a resume document (PDF, DOCX, image) into structured JSON schema containing contact details, work experience, education, skills, and projects. May consume AI credits; do not automatically retry.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file`	No	A user-selected chat attachment supplied by the client. Never invent a download URL or file ID.
`file_url`	No	Actual HTTPS download URL supplied by the client or user. Never use a sandbox path, file ID alone or an invented URL.
`filename`	No	Original filename for base64 data, including extension (PDF, DOCX, PNG or JPG). Inferred from bytes when omitted.
`language`	No	Language code (e.g. 'en', 'ar', 'auto'). Default is 'auto'.	auto
`file_base64`	No	Base64 encoded content of the resume document (PDF, DOCX). Recommended for remote/cloud MCP servers.
`resume_text`	No	Complete resume text read from the attachment. Preferred fallback when the client cannot forward bytes. Do not summarize or invent missing content.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 25, 2026

removedInput schema / properties / api_key

Removed value: -{
-  "description": "Optional API key override.",
-  "type": "string"
-}

Changed20 schema fields changedSep 24, 2026

changedInput schema / anyOf

Previous value: -[
-  {
-    "required": [
-      "resume_text"
-    ]
-  },
-  {
-    "required": [
-      "file_base64"
-    ]
-  },
-  {
-    "required": [
-      "server_file_path"
-    ]
-  }
-]New value: +[
+  {
+    "required": [
+      "resume_text"
+    ]
+  },
+  {
+    "required": [
+      "file_base64"
+    ]
+  },
+  {
+    "required": [
+      "file"
+    ]
+  },
+  {
+    "required": [
+      "file_url"
+    ]
+  }
+]

addedInput schema / properties / file

Added value: +{
+  "additionalProperties": false,
+  "description": "A user-selected chat attachment supplied by the client. Never invent a download URL or file ID.",
+  "properties": {
+    "download_url": {
+      "type": "string"
+    },
+    "file_id": {
+      "type": "string"
+    },
+    "file_name": {
+      "type": "string"
+    },
+    "mime_type": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "download_url",
+    "file_id"
+  ],
+  "type": "object"
+}

addedInput schema / properties / file_url

Added value: +{
+  "description": "Actual HTTPS download URL supplied by the client or user. Never use a sandbox path, file ID alone or an invented URL.",
+  "type": "string"
+}

removedInput schema / properties / filename / default
```
Removed value: -"resume.pdf"
```

changedInput schema / properties / filename / description

Previous value: -"Filename when providing base64 (e.g., 'resume.pdf')."New value: +"Original filename for base64 data, including extension (PDF, DOCX, PNG or JPG). Inferred from bytes when omitted."

changedInput schema / properties / resume_text / description

Previous value: -"Plain text or markdown content of the resume. Easiest option when chatting with an AI agent."New value: +"Complete resume text read from the attachment. Preferred fallback when the client cannot forward bytes. Do not summarize or invent missing content."

addedInput schema / properties / resume_text / minLength
```
Added value: +1
```

removedInput schema / properties / server_file_path

Removed value: -{
-  "description": "Local file path on the MCP server machine. For local CLI/stdio usage only. In ChatGPT or Claude, pass 'resume_text' or 'file_base64' instead.",
-  "type": "string"
-}

removedOutput schema / properties / contact

Removed value: -{
-  "description": "Candidate contact information (name, email, phone, location, links)",
-  "type": "object"
-}

addedOutput schema / properties / data
```
Added value: +{}
```

removedOutput schema / properties / detectedLanguage

Removed value: -{
-  "description": "Primary detected language code (e.g., 'en', 'ar')",
-  "type": "string"
-}

removedOutput schema / properties / education

Removed value: -{
-  "description": "Academic degrees and certifications",
-  "items": {
-    "type": "object"
-  },
-  "type": "array"
-}

removedOutput schema / properties / experience

Removed value: -{
-  "description": "Chronological employment history",
-  "items": {
-    "type": "object"
-  },
-  "type": "array"
-}

removedOutput schema / properties / message

Removed value: -{
-  "description": "Diagnostic or status message",
-  "type": "string"
-}

removedOutput schema / properties / projects

Removed value: -{
-  "description": "Key projects and achievements",
-  "items": {
-    "type": "object"
-  },
-  "type": "array"
-}

removedOutput schema / properties / resumeData

Removed value: -{
-  "description": "Parsed resume sections including contact, experience, education, skills, and projects",
-  "type": "object"
-}

removedOutput schema / properties / skills

Removed value: -{
-  "description": "Technical and domain skills extracted",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedOutput schema / properties / success

Removed value: -{
-  "description": "Whether the document was successfully parsed",
-  "type": "boolean"
-}

removedOutput schema / properties / summary

Removed value: -{
-  "description": "Professional summary statement",
-  "type": "string"
-}

addedOutput schema / required
```
Added value: +[
+  "data"
+]
```

Changed3 schema fields changedSep 15, 2026

changedInput schema / anyOf

Previous value: -[
-  {
-    "required": [
-      "resume_text"
-    ]
-  },
-  {
-    "required": [
-      "file_base64"
-    ]
-  },
-  {
-    "required": [
-      "file_path"
-    ]
-  }
-]New value: +[
+  {
+    "required": [
+      "resume_text"
+    ]
+  },
+  {
+    "required": [
+      "file_base64"
+    ]
+  },
+  {
+    "required": [
+      "server_file_path"
+    ]
+  }
+]

removedInput schema / properties / file_path

Removed value: -{
-  "description": "Local file path on the MCP server machine. Do NOT use for remote cloud servers; use 'resume_text' or 'file_base64' instead.",
-  "type": "string"
-}

addedInput schema / properties / server_file_path

Added value: +{
+  "description": "Local file path on the MCP server machine. For local CLI/stdio usage only. In ChatGPT or Claude, pass 'resume_text' or 'file_base64' instead.",
+  "type": "string"
+}

First observedSep 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation profile is known. The description adds valuable behavioral context beyond annotations: it may consume AI credits and should not be automatically retried. This is a meaningful operational caveat that the annotations cannot express. The description does not detail failure behavior or rate limits, but the credit warning is a strong addition.

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 a single sentence that front-loads the verb and resource, lists the key input and output specifics, and ends with a critical behavioral caveat. Every word earns its place; there is no redundancy or filler.

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 the tool's complexity (6 parameters, nested objects, multiple input modes, output schema exists), the description plus the schema provides sufficient context for correct invocation. The AI-credit warning and retry policy are critical and included. The only small gap is not explicitly mentioning an entitlement prerequisite, but that is covered by sibling tools and not necessary for invoking this specific tool.

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?

Schema description coverage is 100% with detailed parameter descriptions, so the schema carries the semantic load. The tool description adds summary-level context (input formats, output fields) but does not repeat parameter details unnecessarily. The strong schema coverage including warnings like 'never invent a download URL' justifies a score above baseline 3.

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 a specific verb ('Parse'), a resource ('resume document'), and the output ('structured JSON schema containing contact details, work experience, education, skills, and projects'). This distinguishes it from siblings like civify_score_ats or civify_tailor_cv, whose names and purposes are clearly different.

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 lists supported input formats (PDF, DOCX, image) and the output structure, which implies when this tool is appropriate. The schema's anyOf provides clear alternatives for input modes (resume_text, file_base64, file, file_url). The warning 'do not automatically retry' adds operational guidance. However, it does not explicitly state when to prefer this over alternatives like scoring or tailoring, though the purpose difference is self-evident.

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

All Civify tools Inspect

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

Need Help?