Linked API

withdraw_connection_request

Allows you to withdraw the connection request sent to a person (st.withdrawConnectionRequest action). If this workflow is still running, do not retry this tool; retrying can queue duplicate withdrawal attempts for the same person.

Linked API actions are queued into a cloud-browser workflow and may take several minutes. The server returns immediately after starting the workflow with {status: 'pending'|'running', pendingReason, workflowId, operationName, message}. To retrieve the final result, call get_workflow_result with the returned workflowId and operationName — it will long-poll until completion or the request budget elapses, then return either the final result or another in-progress snapshot. Do not retry the original tool while a workflow is still running; that creates duplicate queued work.

A pending workflow carries pendingReason: 'queued' means it is waiting its turn behind other work on the same account and will start within minutes. 'outsideWorkingHours' means the account has configured working hours and the workflow is parked until they reopen — possibly the next working day. In that case get_workflow_result returns immediately instead of polling, message states when the window opens, and you should report that to the user rather than looping.

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": {
      "personUrl": "<personUrl>"
    },
    "name": "withdraw_connection_request"
  }
}

Input Schema

Name	Required	Description	Default
`unfollow`	No	Optional. Boolean indicating whether you want to unfollow the person when withdrawing the request. The default value is true.
`personUrl`	Yes	Public or hashed LinkedIn URL of the person you want to withdraw the connection request from. (e.g., 'https://www.linkedin.com/in/john-doe')

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the readOnlyHint=false and openWorldHint=true annotations, it discloses that the action is queued into a cloud-browser workflow, returns an immediate pending snapshot, and can take minutes. It decodes pendingReason values ('queued' vs 'outsideWorkingHours'), explains that working-hours parking may defer to the next day, and warns that retrying queues duplicate withdrawals. This is exactly the behavioral context annotations cannot carry.

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 purpose is front-loaded in the first sentence and the async contract follows in a logical order. It is long, and the anti-retry warning is repeated in both the first and third paragraphs, slightly diluting the front-loaded structure. Nothing is truly wasted, but the repetition costs it a point.

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, and the description compensates by specifying the returned envelope shape (status, pendingReason, workflowId, operationName, message) and the follow-up call needed for the final result. The remaining gap is functional rather than mechanical: it does not mention the default unfollow behavior, which matters for a mutation on another person's network state.

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 personUrl and unfollow are already documented, and the baseline is 3. The description adds nothing parameter-specific beyond 'sent to a person'; notably it never mentions that unfollow defaults to true, a non-obvious side effect on the target person.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: withdrawing a connection request previously sent to a person, with the underlying action named (st.withdrawConnectionRequest). An agent can distinguish this from adjacent tools by the word 'withdraw'. It does not explicitly contrast with remove_connection or ignore_invitation, which look similar, so sibling differentiation is only implied.

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 clear operating conditions: use it to withdraw a sent request, and explicitly do not retry while the workflow is running. It also routes the agent to get_workflow_result with the returned workflowId and operationName. It stops short of naming when to use remove_connection or ignore_invitation instead, which would have closed the loop with siblings.

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

All Linked API 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.