Skip to main content
Glama

Withdraw your OWN submission to a form (consequential, cannot be undone)

ic_forms_withdraw
Destructive

Take your human's own submission back. NO TOKEN REQUIRED, and no token grants this on anyone else's behalf: the ONLY things that open a record here are your human's signed-in identity or the submission_id plus the one-time claim_token handed back at submit. An operator cannot do it for them, a reviewer cannot do it for them, and admin:forms_manage does not reach this — withdrawing belongs to the person who submitted, because a reviewer withdrawing on somebody's behalf is a rejection wearing that person's name. CONFIRM WITH YOUR HUMAN BEFORE CALLING, in the plainest words you have. THIS CANNOT BE UNDONE BY ANYONE HERE: no reviewer can move a withdrawn record back, and on a form that asks for an email address, answering again on that address is REFUSED, so a withdrawal is not a way to redo an application. If they had been APPROVED, withdrawing hands their place back to the group and somebody on the waitlist can take it — freed_slot in the response tells you whether that happened, and it is the sentence to read to them. Idempotent: a record that was already withdrawn comes back ok with changed: false rather than an error, so a retry after a timeout is safe. A wrong id, a wrong token and an id that was never issued all return the same found: false, so this cannot be used to test which ids exist. Args: { form_id, submission_id?, claim_token? }. Returns: { ok, found, submission_id?, status?, previous_status?, changed?, already_withdrawn?, freed_slot?, counts?, message }. No auth required.

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": {
      "form_id": "<form_id>"
    },
    "name": "ic_forms_withdraw"
  }
}

Input Schema

NameRequiredDescriptionDefault
form_idYesWhich form.
claim_tokenNoThe one-time token returned at submit. Must be sent WITH submission_id; either alone withdraws nothing.
submission_idNoNeeded only when the submitter has no IC account. A signed-in submitter needs neither this nor the token.

Output Schema

NameRequiredDescriptionDefault
okNotrue when the call did what it was asked; false with `error` and `error_kind` when it did not
textNoThe tool's reply when it returns plain text instead of JSON
errorNoWhy the call failed, in a sentence a person can act on. Present only when ok is false.
resultNoThe tool's value when it returns a list or a single value instead of an object
error_kindNoMachine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "description": "The tool's JSON result. Every field the tool's description names is present at the top level; ok, error and error_kind follow the shared envelope.",
      +  "properties": {
      +    "error": {
      +      "description": "Why the call failed, in a sentence a person can act on. Present only when ok is false."
      +    },
      +    "error_kind": {
      +      "description": "Machine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient"
      +    },
      +    "ok": {
      +      "description": "true when the call did what it was asked; false with `error` and `error_kind` when it did not"
      +    },
      +    "result": {
      +      "description": "The tool's value when it returns a list or a single value instead of an object"
      +    },
      +    "text": {
      +      "description": "The tool's reply when it returns plain text instead of JSON"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, so the description's job is added context, and it delivers: who can and cannot perform the withdrawal, that no reviewer can reverse it, that re-answering is refused on email forms, that an approved slot is freed to the waitlist, and that found:false masks wrong-id probes. The retry-safety claim sits in mild tension with idempotentHint=false, though it is framed narrowly around the already-withdrawn case.

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 irreversible warning and the confirm-with-your-human instruction are front-loaded ahead of the mechanics, which is the right ordering. There is some redundancy: the "operator cannot / reviewer cannot / admin:forms_manage does not reach this" triplet restates the earlier exclusivity claim, and the trailing Returns list duplicates the output schema.

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 destructive, no-auth-required mutation this covers everything an agent needs: the trigger to call, the confirm step, the auth paths, irreversibility, the freed_slot consequence to relay, and the enumeration-safe error shape. An output schema exists, so not restating field types is correct.

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 the mutual-dependency rule the schema only half-states: claim_token must travel with submission_id, and either alone withdraws nothing, while a signed-in submitter needs neither. That is real semantic value on top of the field descriptions.

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?

"Take your human's own submission back" names a specific verb and resource and immediately bounds the scope to the caller's own record. That single sentence separates it from submit, from reviewer-side rejection, and from any admin_manage path, without the agent needing a schema.

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 explicit when-not guidance: it is not a way to redo an application, and it must be confirmed with the human first. Auth-path selection is also spelled out (signed-in identity vs. submission_id + claim_token). It stops short of naming a sibling to use instead for resubmission, which keeps it from a 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.