Aide

Update an AI agent

update_agent

Destructive

Change how an AI agent answers. Only the fields given change; instructions and lists replace the previous ones, so start from get_agent's. A deployed agent uses the new settings at once. Returns the agent; suggest test_agent next.

Input Schema

Name	Required	Description
`name`	No	The name customers see.
`model`	No	`fast` answers sooner on a lighter model; null for the default.
`agentId`	Yes	The agent id, from list_agents.
`greeting`	No	The first chat message visitors see.
`teamName`	No	The team the agent signs as, such as `Acme Support`.
`signature`	No	The sign-off on email replies.
`description`	No	A note for teammates on what the agent is for.
`instructions`	No	How it answers, in plain words: tone, policies, what to hand to a person.
`botIdentifier`	No	What it calls itself when asked, such as `AI agent`.
`usePastTickets`	No	Draw on how the team answered past conversations.
`collectedFields`	No	Custom fields to collect in chat, in order (list_custom_fields ids).
`suggestedActions`	No	Chat buttons visitors can tap.
`knowledgeSetNames`	No	Knowledge source names (list_knowledge_sources); empty for all.
`contactInformation`	No	How customers reach a person, for when the agent hands over.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026
- changedInput schema / properties / instructions / maxLength
```
Previous value: -20000New value: +6000
```

Changed7 schema fields changedOct 26, 2026

addedInput schema / properties / botIdentifier

Added value: +{
+  "description": "What it calls itself when asked, such as `AI agent`.",
+  "maxLength": 60,
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedInput schema / properties / collectedFields

Added value: +{
+  "description": "Custom fields to collect in chat, in order (list_custom_fields ids).",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "fieldId": {
+        "maxLength": 64,
+        "type": "string"
+      },
+      "mode": {
+        "enum": [
+          "extract",
+          "ask_if_missing",
+          "always_ask"
+        ],
+        "type": "string"
+      },
+      "required": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "fieldId"
+    ],
+    "type": "object"
+  },
+  "maxItems": 50,
+  "type": "array",
+  "uniqueItems": true
+}

changedInput schema / properties / instructions / description

Previous value: -"How the agent answers, in plain words (at most 20,000 characters)."New value: +"How it answers, in plain words: tone, policies, what to hand to a person."

addedInput schema / properties / knowledgeSetNames

Added value: +{
+  "description": "Knowledge source names (list_knowledge_sources); empty for all.",
+  "items": {
+    "maxLength": 120,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / model

Added value: +{
+  "description": "`fast` answers sooner on a lighter model; null for the default.",
+  "enum": [
+    "fast",
+    "standard",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedInput schema / properties / suggestedActions

Added value: +{
+  "description": "Chat buttons visitors can tap.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "question": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "shortcut": {
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "shortcut",
+      "question"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "type": "array"
+}

addedInput schema / properties / usePastTickets

Added value: +{
+  "description": "Draw on how the team answered past conversations.",
+  "type": "boolean"
+}

AddedOct 20, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantive behavior beyond the destructiveHint annotation: partial-update semantics (only given fields change), replace-not-merge semantics for instructions and lists, and immediate effect on a deployed agent. The replacement warning is exactly the risk an agent needs flagged before a destructive write.

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?

Four short sentences, each carrying distinct information: purpose, partial-update rule, propagation timing, and next step. Nothing is redundant and the key constraint is front-loaded.

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 14-parameter destructive mutation with no output schema, the description covers return value (the updated agent), overwrite hazards, and immediate deployment effect. No output schema explanation is needed since it states the return.

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 field meanings are already documented and the baseline is 3. The description earns above baseline by explaining that instructions and list-valued fields overwrite rather than merge — semantics the schema does not encode — though it doesn't name which parameters are the list-valued ones.

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?

"Change how an AI agent answers" gives a specific verb and resource, and the mention of get_agent/test_agent situates it among siblings. Slightly narrow framing — the tool also edits name, description, and teamName, not just answering behavior — but an agent can still identify it immediately.

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?

Clearly says to start from get_agent's current values and to follow up with test_agent, which is real workflow routing. It does not address when-not-to-use cases (e.g., deploy_agent for deployment, or pause_agent for disabling), so it stops short of full exclusion guidance.

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

All Aide 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.

Update an AI agent

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources