Skip to main content
Glama
Sign In
@proof-holdings/mcp-server

@proof-holdings/mcp-server

Official
by ProofHoldings
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

wait_for_confirmation

Read-only

Polls a confirmation ID until the approver responds, returning approved, denied, or pending after create_confirmation. Retries with backoff until timeout so agents can wait for human authorization.

Instructions

Poll a confirmation until the approver responds. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter.

Agent usage: Call this after create_confirmation with the returned confirmation ID. Terminal states: "approved" (action authorized — check the proof_token), "denied" (action rejected). While "pending", the approver has not yet responded. This poll returns no link — the approval request is delivered to the approver's own channel, and only the owner's "Send again" (POST /api/v1/confirmations/{id}/resend, which no tool calls yet) delivers it there again. If the owner will decide instead, call get_confirmation_approval_link for the owner's approval_url; it needs the confirmation to be still pending — the state this tool waits in — and also refuses once timeout_at has passed, so a long wait can outlive the link even while the status has not moved.

ACCESS: needs a Proof account. Set PROOF_API_KEY and restart this server, then call this tool again. start_login does NOT open this tool.

Input Schema

NameRequiredDescriptionDefault
idYesConfirmation ID from create_confirmation
timeout_secondsNoMaximum wait time in seconds (default: 50, max: 600). Keep it under your MCP client's request timeout (the SDK default is 60 s) — a longer wait is cut off by the client while the server is still polling. On timeout the tool answers status "pending"; call it again with the same identifier.

Output Schema

NameRequiredDescriptionDefault
idNoMongoDB ObjectId
statusNo"pending" when the wait ran out before a terminal state; otherwise the resource's own status
hitl_idNo
messageNoOn timeout: what to do next (call the tool again with the same identifier)
resendsNoEvery "Send again" (`POST /confirmations/{id}/resend`), oldest first, the last 50 kept. Absent from an API that predates it.
responseNoThe decision and its evidence (null while pending)
created_atNo
timeout_atNoWhen this confirmation will time out
updated_atNo
last_statusNoOn timeout: the last non-terminal status observed, or null when none was
proof_tokenNoSigned proof of the decision, approval or denial alike, naming who decided (`decided_by`, plus `authorization_id` for an approver); null while pending and for a system denial (`response.channel` is `system`)
resolved_atNo
waited_secondsNoOn timeout: seconds actually waited
timeout_secondsNoOn timeout: the wait budget this call was given

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "created_at": {},
+    "hitl_id": {},
+    "id": {
+      "description": "MongoDB ObjectId"
+    },
+    "last_status": {
+      "description": "On timeout: the last non-terminal status observed, or null when none was"
+    },
+    "message": {
+      "description": "On timeout: what to do next (call the tool again with the same identifier)"
+    },
+    "proof_token": {
+      "description": "Signed proof of the decision, approval or denial alike, naming who decided (`decided_by`, plus `authorization_id` for an approver); null while pending and for a system denial (`response.channel` is `system`)"
+    },
+    "resends": {
+      "description": "Every \"Send again\" (`POST /confirmations/{id}/resend`), oldest first, the last 50 kept. Absent from an API that predates it."
+    },
+    "resolved_at": {},
+    "response": {
+      "description": "The decision and its evidence (null while pending)"
+    },
+    "status": {
+      "description": "\"pending\" when the wait ran out before a terminal state; otherwise the resource's own status"
+    },
+    "timeout_at": {
+      "description": "When this confirmation will time out"
+    },
+    "timeout_seconds": {
+      "description": "On timeout: the wait budget this call was given"
+    },
+    "updated_at": {},
+    "waited_seconds": {
+      "description": "On timeout: seconds actually waited"
+    }
+  },
+  "type": "object"
+}
  2. First observedv1.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, and the description is consistent with a non-mutating poll while adding substantial behavior: exponential backoff parameters (2s initial, 1.5x, 30s max, jitter), what 'pending' means, that the call returns no link and the request is delivered to the approver's own channel, and the resend path that no tool currently covers. It also discloses the auth prerequisite (PROOF_API_KEY) and that start_login cannot satisfy it, which is behavior the annotations do not 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?

Front-loaded with the core action and backoff behavior, then clearly sectioned into 'Agent usage:' and 'ACCESS:'. The aside about the resend endpoint and the parenthetical 'which no tool calls yet' is useful context but is the one passage that could be trimmed without losing callable information.

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 polling tool with an output schema, the description covers everything an agent needs: when to start, what states to expect, how long to wait relative to client timeouts, what is not returned, and the account prerequisite. Return-value documentation is correctly left to the output schema.

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 both id and timeout_seconds are already fully documented, including the under-client-timeout advice. The description reinforces the id's origin ('from create_confirmation') but adds no format, value, or edge-case detail beyond the schema, which is the expected baseline when the schema does the work.

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 ('Poll a confirmation') plus the exact condition bounding it ('until the approver responds'). It also enumerates the terminal states (approved/denied) and names the sibling it is not (get_confirmation_approval_link), so an agent can distinguish it from the other confirmation tools without opening 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit precondition ('Call this after create_confirmation with the returned confirmation ID') and a named alternative with the condition that selects it ('If the owner will decide instead, call get_confirmation_approval_link'). It also states an exclusion ('start_login does NOT open this tool') and warns that the link path fails once timeout_at passes while this tool keeps waiting.

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

Deploy Server

Other Tools