FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT

Check how hiring software reads a resume

resume_check

Read-onlyIdempotent

Checks resume text for machine-readable sections, recognized skills, contact channels, a headline, and experience date ranges using FoundRole's deterministic parser.

Pass resume_text to check plain text supplied in the conversation. If resume_text is omitted, the tool reads the previously extracted text of the primary resume in the authenticated user's FoundRole account. It returns a readability band (strong, good, partial) and the single biggest loss. Depending on the account it also returns additional findings and the parsed facts (headline, years of experience, sections, contact channels, recognized skill count). Each finding includes a suggested fix. A saved report link is returned only when the account already has access to that report. This is FoundRole's text-readability assessment, not a test against a named ATS, a hiring prediction, or a file-layout check. Pasted text does not preserve the original PDF or DOCX layout.

The tool does not upload a file, create a saved resume or report, change the user's profile, submit an application, or fetch URLs found in the text. It may return a FoundRole website link; opening that link and uploading or editing a resume are separate user actions. Operational request records and diagnostics may retain tool inputs; this tool does not promise that submitted text is never stored.

Input Schema

Name	Required	Description	Default
`resume_text`	No	Plain text of the resume to check, when it is available in the conversation. Omit to check the resume uploaded to the user's FoundRole account. Minimum 200 characters.

Output Schema

Name	Required	Description	Default
`band`	No
`mode`	Yes
`findings`	No
`parsedAs`	No
`profileSetupUrl`	No
`studioReportUrl`	No
`system_instruction`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 9, 2026
- addedOutput schema / properties / findings / items / properties / fix
```
Added value: +{
+  "type": "string"
+}
```
- removedOutput schema / properties / limited
```
Removed value: -{
-  "type": "boolean"
-}
```
- removedOutput schema / properties / moreFindings
```
Removed value: -{
-  "type": "integer"
-}
```
- addedOutput schema / properties / profileSetupUrl
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
- removedOutput schema / properties / uploadUrl
```
Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
```
AddedOct 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare the safe read-only/idempotent profile, yet the description adds real behavioral context beyond them: the parse is deterministic (not a named-ATS simulation), the report link appears only when the account has access, pasted text loses PDF/DOCX layout, and inputs may be retained in operational logs. This level of disclosure is far above the annotation baseline.

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 and the two usage modes, and most sentences carry non-redundant scope or retention information. It is somewhat long and the negative-scope claims ('not a named ATS... not a file-layout check' plus the 'does not upload/create/change/submit/fetch' list) overlap enough that a tighter phrasing would lose nothing.

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?

Even though an output schema exists, the description still names the return shape (readability band, biggest loss, findings with suggested fixes, parsed facts) and covers retention and safety. For a low-complexity one-param tool with annotations and an output schema, 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.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the single resume_text parameter, its omit-to-use-account fallback, and the 200-character minimum are already documented in the schema. The description restates this rather than adding syntax or format detail beyond it, so the 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 ('Checks') and resource ('resume text') plus the exact facets examined: machine-readable sections, recognized skills, contact channels, headline, and experience date ranges. No sibling overlaps with this capability, and the description also explicitly bounds what it is not (not an ATS test, hiring prediction, or layout check).

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

Usage Guidelines5/5

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

Explicitly distinguishes the two invocation modes: pass resume_text for conversation-supplied text, omit it to read the account's primary resume. It also states exclusions (no upload, no saved resume/report, no application submission, no URL fetching), so the agent knows when this tool is and is not appropriate.

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

All FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT 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.