Job Spotter

Use the person's own CV or cover letter file for one application

replace_application_document

Use the person's own CV or cover letter file for one application. When the person wants to send their own file ("use my designed CV for this one") instead of the one Job Spotter wrote. Send the file base64-encoded (.pdf or .docx, up to 1 MB; .txt and .md also work). Its text is read into the application for matching and form answers; a PDF or Word file goes to the employer exactly as it is (by email, the application robot and the document links). Only for this application: the saved CV stays as it was (use upload_cv to change that). A later text edit to the same document replaces the file. Gives a new revision: show the person the text read, then apply with that expected_revision. A ready-to-read summary is in say.

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": {
      "application_id": "<application_id>",
      "kind": "<kind>",
      "file_base64": "<file_base64>",
      "filename": "<filename>"
    },
    "name": "replace_application_document"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	Which document to replace.
`filename`	Yes	File name with its extension, for example "Ana Silva CV.pdf".
`file_base64`	Yes	The person's file, base64-encoded.
`application_id`	Yes	The application id (app_...).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the generic profile (not read-only, not destructive, not idempotent, open-world); the description adds the real operational facts: the text is parsed for matching and form answers, a PDF/Word file is delivered verbatim to the employer by email/robot/links, a later text edit overwrites the file, and the call returns a new revision. It also flags the size/format limits and that the agent must show the person the read text before applying.

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?

Purpose and trigger are front-loaded in the first two sentences, with constraints and side effects following in a logical order. It is dense and slightly longer than needed, but nearly every sentence carries a distinct operational fact.

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?

No output schema exists, yet the description covers what comes back (a new revision, plus a ready-to-read summary in `say`) and the required follow-up (apply with that expected_revision). For a four-required-parameter write tool with an open-world hint, the agent has everything needed to call it correctly and explain the result.

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 compensates for the terse schema by supplying the file constraints (.pdf or .docx up to 1 MB, .txt/.md also work) and the semantic of `kind` (CV vs cover letter being replaced) and of expected_revision downstream. Filename convention is only covered by the schema, so not a 5.

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 and resource — use the person's own CV or cover letter file for one application — and draws an explicit line against upload_cv (which changes the saved CV). An agent can distinguish it from cover_letter and upload_cv 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?

Gives an explicit trigger ("when the person wants to send their own file ... instead of the one Job Spotter wrote") and an explicit exclusion with the alternative named ("Only for this application: the saved CV stays as it was (use upload_cv to change that)"). No inference required.

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

All Job Spotter 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.