Plori

Official

by plori-ai

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Answer pending question

answer_pending_input

Destructive

Answer a paused run's human-input request: provide a value for a question or set approved=false to deny. Only the account owner can approve; returns a new run ID.

Instructions

Answer a run that is paused on a human-input request (from list_pending_inputs). Use approved=false to deny an action, or value to answer a question. Only the account owner can approve an action in the Plori web app. Show them the pending input's approve_url. Never ask for or submit a secret value through this tool. Use the Plori web app for secrets and connections. A successful answer starts a continuation run: the returned run_id is that new continuation run, not the parked run, and is the id to poll with get_run_result.

Input Schema

TableJSON Schema

Name	Required	Description
`note`	No	An optional note recorded with the answer.
`value`	No	For an input request: the value to supply.
`run_id`	Yes	The parked run's id.
`approved`	No	For an approval request: set false to deny. Only the owner can approve in the Plori web app.
`tool_call_id`	Yes	The tool_call_id of the pending request (from list_pending_inputs).
`max_turn_seconds`	No	Optional soft wall-clock budget to preserve on the continuation run; it does not change the parked run or impose a hard deadline.

Output Schema

TableJSON Schema

Name	Required	Description
`run_id`	No	The continuation run created by the answer.
`status`	Yes	Answer status.
`already`	No	Whether this request had already been answered.
`session_id`	No	The continuation run's session.
`tool_call_id`	Yes	The pending tool call that was answered.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.17.0Oct 1, 2026

removedInput schema / properties / always_allow

Removed value: -{
-  "description": "Approve AND stop asking for this tool on this agent (a standing grant). Only set it when the human explicitly said to stop being asked, and only on a row whose consent_tool is set; ignored without approved=true. Revoke via DELETE /v1/agents/{agent_id}/tool-consents/{tool}.",
-  "type": "boolean"
-}

changedInput schema / properties / approved / description

Previous value: -"For an approval request: approve (true) or deny (false)."New value: +"For an approval request: set false to deny. Only the owner can approve in the Plori web app."

removedInput schema / properties / scope

Removed value: -{
-  "description": "Set to \"thread\" to approve AND allow the rest of this conversation's writes to the same connection, method and host, instead of a standing grant. It expires after 24 hours and covers no other host, method or conversation. Only set it when the human said to stop being asked for the rest of this task; ignored without approved=true, and on a card that has no such scope. Cannot be combined with always_allow.",
-  "type": "string"
-}

Changed2 schema fields changedv0.16.0Sep 19, 2026

addedInput schema / properties / scope

Added value: +{
+  "description": "Set to \"thread\" to approve AND allow the rest of this conversation's writes to the same connection, method and host, instead of a standing grant. It expires after 24 hours and covers no other host, method or conversation. Only set it when the human said to stop being asked for the rest of this task; ignored without approved=true, and on a card that has no such scope. Cannot be combined with always_allow.",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "already": {
+      "description": "Whether this request had already been answered.",
+      "type": "boolean"
+    },
+    "run_id": {
+      "description": "The continuation run created by the answer.",
+      "type": "string"
+    },
+    "session_id": {
+      "description": "The continuation run's session.",
+      "type": "string"
+    },
+    "status": {
+      "description": "Answer status.",
+      "type": "string"
+    },
+    "tool_call_id": {
+      "description": "The pending tool call that was answered.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "tool_call_id"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.9.1Aug 20, 2026

addedInput schema / properties / max_turn_seconds

Added value: +{
+  "description": "Optional soft wall-clock budget to preserve on the continuation run; it does not change the parked run or impose a hard deadline.",
+  "maximum": 14400,
+  "minimum": 0,
+  "type": "integer"
+}

Changed1 schema field changedv0.7.0Aug 9, 2026

addedInput schema / properties / always_allow

Added value: +{
+  "description": "Approve AND stop asking for this tool on this agent (a standing grant). Only set it when the human explicitly said to stop being asked, and only on a row whose consent_tool is set; ignored without approved=true. Revoke via DELETE /v1/agents/{agent_id}/tool-consents/{tool}.",
+  "type": "boolean"
+}

First observedv0.1.0Jul 4, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, non-idempotent, and openWorld, so the safety profile is covered. The description adds genuinely non-structured context: that only the account owner can approve (in the web app), that secrets must not be passed here, and that a successful answer spawns a continuation run. This is strong added value beyond annotations.

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-loaded with the action and the sibling reference, then flows through denial, auth constraint, secret exclusion, and return semantics. Every sentence carries a distinct actionable fact with no filler.

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?

An output schema exists so return values need not be explained, yet the description still clarifies the one thing that would otherwise confuse an agent: which run_id to poll afterwards. Combined with auth and secret guidance, nothing needed to invoke correctly is missing.

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 3 baseline applies, but the description adds meaning beyond the schema: the deny semantics of approved=false, value being the question answer, and critically the note that the returned run_id is the continuation run's id, not the parked run's. That resolution of the run_id ambiguity is real added value.

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 ('Answer a run that is paused on a human-input request') and immediately cross-references the sibling list_pending_inputs that produces the required tool_call_id. An agent can place it precisely among siblings like list_pending_inputs, cancel_run, and get_run_result.

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 explicit routing: approved=false to deny, value to answer a question, and a clear exclusion for secrets/connections ('Use the Plori web app for secrets and connections'). It also names the follow-up tool (get_run_result) needed after a successful answer.

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