MaxCV.ai

score_cv

Assess only the supplied CV against atomic job requirements using Jev evidence probabilities. Returns one source score, assessmentKind=source_only, method=jev-probability-v1 and per-requirement met/not_met/unknown probabilities, confidence and actual model version. Every requirement stays in the denominator; the score is 100 times mean probabilityMet. No tailored CV or after score is generated. Run tailor_cv for actual document before/after assessment.

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": {
      "cvText": "<cvText>",
      "jobDescription": "<jobDescription>"
    },
    "name": "score_cv"
  }
}

Input Schema

Name	Required	Description	Default
`cvText`	Yes	The full CV/resume as plain text.
`jobDescription`	Yes	The job posting text.

Schema Changelog

Changes observed during successful MCP inspections.

First observedJun 17, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it specifies the scoring formula ('100 times mean probabilityMet'), the treatment of unmet requirements ('every requirement stays in the denominator'), the method identifier, and that the actual model version is returned. It does not cover cost/latency or failure behavior for malformed CV text, which keeps it below a 5.

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 scope and the sibling exclusion are front-loaded, and every sentence carries information about output shape or scoring semantics. Some jargon ('Jev evidence probabilities', 'method=jev-probability-v1') is dense for a reader unfamiliar with the method, but it maps to returned fields rather than being 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?

There is no output schema, so the description must describe returns, and it enumerates the key fields (source score, assessmentKind, method, per-requirement probabilities, confidence, model version) plus the scoring formula. The structure of the per-requirement probability objects and the meaning of 'confidence' remain unspecified, which is a minor gap for an otherwise self-contained two-parameter tool.

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 both parameters (cvText, jobDescription) are documented in the schema, so the description need not repeat them. The description adds no meaning about input format, size limits, or what constitutes an 'atomic job requirement' that the agent must extract or supply, so the baseline of 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?

The description opens with a specific verb+resource combination ('Assess only the supplied CV against atomic job requirements') and immediately scopes it ('only the supplied CV'), which separates it cleanly from the tailor_cv sibling. An agent can tell what this tool produces (a source score, not a tailored document) without opening any schema.

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?

It states both the when ('Assess only the supplied CV') and the when-not with the named alternative: 'No tailored CV or after score is generated. Run tailor_cv for actual document before/after assessment.' This is an explicit routing rule to the sibling, not an implied one.

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

All MaxCV.ai 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?