Skip to main content
Glama

SourceGeek

Score candidates

score_leads
Destructive

Score every candidate in an existing SourceGeek sheet against a job description or hiring criteria, writing a Score column (with reasoning) back to the sheet; scoring a sheet again replaces its earlier scores. Rows without full profile data are first enriched from public profiles, billed per profile. Pass the sheet's artifactId and the requirements as text (fetch a job posting URL yourself first). Spends credits per scored row. Scoring runs in the background: if it has not finished within a minute the result says status 'running' — read the sheet again later to see the scores.

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": {
      "artifactId": "<artifactId>",
      "targetDescription": "<targetDescription>"
    },
    "name": "score_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
artifactIdYesThe artifact id to score. Required; do not score an implicit latest sheet.
targetDescriptionYesThe job description, role requirements, hiring criteria. Do not pass URLs here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the destructive/openWorld annotations it discloses real consequences: prior scores are overwritten, missing profiles are enriched and billed per profile, credits are spent per scored row, and scoring is asynchronous with a 'running' status if it exceeds a minute. These are exactly the cost and side-effect facts an agent needs before invoking a destructive, credit-spending tool.

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 core action and its artifactId/requirements inputs come first, followed by side effects and the background-execution caveat, with no filler. It is dense and semicolon-chained rather than cleanly separated into sentences, which costs a point on readability.

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?

For a two-parameter mutation with no output schema, everything needed to call it correctly is present: cost model, overwrite semantics, enrichment behavior, and how to interpret the returned status when scoring has not finished.

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 coverage is 100%, so the baseline is 3, but the description adds usable meaning: the requirements must be plain text, not a URL the tool will fetch, and the sheet must be identified explicitly rather than defaulted to the latest. That is genuine guidance layered on top of the schema.

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 states a specific verb and resource — scoring every candidate in an existing SourceGeek sheet against a job description — and explicitly scopes it to a sheet rather than implicit search results, which distinguishes it from the search/shortlist siblings.

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?

It is clear on preconditions (must have an existing sheet, must supply artifactId, must fetch a job posting URL yourself before calling) and on repeat behavior (re-scoring replaces earlier scores). It stops short of naming an alternative tool for agents who do not yet have a sheet, so 4 rather than 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources