Actual group – offres d'emploi

Start a job application

start_application

Idempotent

Prepare an application to an Actual group offer on behalf of the candidate you are assisting. Returns a personal link, valid 72 hours, that the candidate must open to attach their CV and give consent to the processing of their data; the application is only sent once they submit that page. Only call this when the candidate has asked to apply and given you their name and email. Never submit the page yourself: give the link to the candidate.

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": {
      "slug": "<slug>",
      "firstName": "<firstName>",
      "lastName": "<lastName>",
      "email": "<email>"
    },
    "name": "start_application"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Language of the application page. Defaults to fr.
`slug`	Yes	Slug of the offer, from search_offers or get_offer.
`email`	Yes	Candidate email address.
`lastName`	Yes	Candidate last name.
`firstName`	Yes	Candidate first name.
`phoneNumber`	No	Candidate phone number, optional.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 9, 2026

removedInput schema / properties / context

Removed value: -{
-  "description": "Why are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.",
-  "type": "string"
-}

removedInput schema / properties / conversation_id

Removed value: -{
-  "description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.",
-  "type": "string"
-}

removedInput schema / properties / llm_model

Removed value: -{
-  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "slug",
-  "firstName",
-  "lastName",
-  "email",
-  "context",
-  "llm_model"
-]New value: +[
+  "slug",
+  "firstName",
+  "lastName",
+  "email"
+]

Changed1 schema field changedOct 23, 2026

changedInput schema / properties / context / description

Previous value: -"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""New value: +"Why are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers."

Changed4 schema fields changedOct 22, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "slug",
-  "firstName",
-  "lastName",
-  "email"
-]New value: +[
+  "slug",
+  "firstName",
+  "lastName",
+  "email",
+  "context",
+  "llm_model"
+]

First observedOct 16, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the deferred-completion model: the tool returns a personal link valid 72 hours, the application is not actually sent until the candidate opens the page, attaches a CV, and consents to data processing. That consent/data-handling detail and the human-in-the-loop constraint are exactly the kind of context annotations cannot express.

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?

Front-loads the action, then the return contract, then the gating and prohibition, in three dense sentences with no filler. Nothing could be removed without losing an operative constraint.

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?

With no output schema, the description compensates by explaining the return value (a personal link, 72-hour validity) and the asynchronous nature of the actual submission. For a mutation tool with no output schema, this is complete enough to call correctly.

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%, including the origin of the slug ('from search_offers or get_offer') and the lang default, so the schema carries the parameter burden. The description adds only the framing that firstName/lastName/email belong to the candidate; baseline 3 is appropriate.

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 (prepare/start an application) plus the resource (an offer from Actual group) and the actor (on behalf of the candidate being assisted). This is clearly distinguishable from the read-only discovery siblings (search_offers, get_offer, find_agencies), which only surface offers.

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?

Gives an explicit precondition: only call when the candidate has asked to apply and supplied name and email, and an explicit behavioral rule: never submit the page, hand the link to the candidate. It does not name a sibling alternative for the discovery step, but the gating conditions are unambiguous.

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

All Actual group – offres d'emploi 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?