Skip to main content
Glama
Sign In

Aide

by app.aide
OverviewDiscussionsAdmin

Update a conversation

update_conversation
Destructive

Change a conversation's status, priority, assignee, team or custom fields, as the signed-in teammate; only the fields given change. Closing it may send the customer a satisfaction survey when the workspace's CSAT settings ask for one. It can't snooze: the only tool that snoozes is reply_to_conversation, and only while it sends the customer a reply. Returns the updated conversation.

Input Schema

NameRequiredDescriptionDefault
statusNoThe new status. `on_hold` takes an onHoldReason; `snoozed` needs a time, which this tool does not take.
teamIdNoA team id from list_members, or null for no team.
priorityNoThe new priority.
assigneeIdNoA teammate id from list_members, or null to unassign.
fieldValuesNoCustom field values as { key, value }; a null value clears one.
onHoldReasonNoWhy the conversation is on hold, with status `on_hold`.
conversationIdYesThe Aide conversation id (`cnv_…`), from find_conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / fieldValues
      Added value: +{
+  "description": "Custom field values as { key, value }; a null value clears one.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "key": {
+        "maxLength": 64,
+        "minLength": 1,
+        "type": "string"
+      },
+      "value": {
+        "anyOf": [
+          {
+            "type": "null"
+          },
+          {
+            "items": {
+              "maxLength": 120,
+              "type": "string"
+            },
+            "maxItems": 200,
+            "type": "array"
+          },
+          {
+            "type": "boolean"
+          },
+          {
+            "maxLength": 500,
+            "type": "string"
+          },
+          {
+            "type": "number"
+          }
+        ],
+        "type": [
+          "null",
+          "array",
+          "boolean",
+          "string",
+          "number"
+        ]
+      }
+    },
+    "required": [
+      "key",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 100,
+  "type": "array"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / priority / type
      Added value: +"string"
    • addedInput schema / properties / status / type
      Added value: +"string"
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description goes beyond them by disclosing the CSAT survey side effect on closing, the partial-update merge semantics, and that the updated conversation is returned. It still doesn't say whether a close is reversible or what permissions are required, so not a 5.

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?

Three short sentences, front-loaded with the action and scope, followed by the riskiest side effect disclosure and the return value. No filler, and the snooze clause is compact despite doing real disambiguation work.

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?

With no output schema, the 'Returns the updated conversation' line is necessary and present, and the mutation's side effect is disclosed. For a destructive 7-parameter mutation it could still say more about reversibility and failure behavior, but an agent has enough to call it 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%, so every parameter is already documented, including the snoozed/onHoldReason caveat. The description's field list and snooze remark largely restate the schema; only the 'only the fields given change' merge rule adds semantics beyond it.

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 concrete verb ('Change') with the exact mutable fields (status, priority, assignee, team, custom fields) and the acting identity (signed-in teammate). It also names the sibling that owns the one capability it lacks (reply_to_conversation for snoozing), so the agent can tell it apart without opening schemas.

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?

The partial-update rule ('only the fields given change') and the explicit snooze exclusion give clear conditions for use and non-use, with the alternative named. What's missing is guidance on when to prefer this over reply_to_conversation for status changes that accompany a reply, or any prerequisite such as fetching the conversation first.

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

All Aide toolsInspect
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