Skip to main content
Glama

Change an AI agent's greeting or prompt

agent_update
DestructiveIdempotent

Changes what a live AI voice agent says: its greeting (the first line it speaks), its system prompt (its instructions), or, on realtime agents, its welcome_instruction (how it opens the call). Tools, transfers, voice, language, webhooks and audio settings cannot be changed here; they are edited in the portal. The change applies from the next call. With dryRun: true it returns the exact before and after of every setting that would change, plus a baseVersion, and changes nothing. With dryRun: false and that baseVersion it applies the change; it is refused if the agent changed since the preview, or if anything other than the named fields would change.

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": {
      "agent_id": "<agent_id>"
    },
    "name": "agent_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
dryRunNoIf true, return the exact diff without changing the agent
agent_idYesThe agent's id
baseVersionNoRequired to apply: the baseVersion from this tool's dryRun preview
system_promptNoThe agent's full instructions. Replaces the current prompt in full
greeting_messageNoThe exact first line the agent speaks on every call
welcome_instructionNoRealtime agents only: an instruction for how to open the call

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / agent_id / description
      Previous value: -"The agent's id, from agent_list"New value: +"The agent's id"
    • changedInput schema / properties / system_prompt / description
      Previous value: -"The agent's full instructions. REPLACES the current prompt — preview it first"New value: +"The agent's full instructions. Replaces the current prompt in full"
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is partly structured. The description does add meaningful context beyond that: the change takes effect on the next call, dryRun returns a before/after diff plus baseVersion and mutates nothing, and the apply is refused on a stale agent or unexpected field drift. However, the destructiveHint=true framing is softened only implicitly (the refusal-on-drift guarantee) and it never says that overwriting system_prompt is irreversible or that no rollback exists.

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 action, followed by exclusions, timing, and the dry-run contract in a logical order. It is dense but each clause earns its place; slightly long as a single paragraph without visual separation of the workflow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers scope, exclusions, timing, and the dryRun/apply protocol thoroughly for a 6-parameter mutation tool with no output schema; the description usefully describes the dryRun return shape. It stops short on error/refusal semantics and on whether the prompt overwrite is recoverable, which matter for a destructive tool.

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 goes further by explaining the coupling between dryRun and baseVersion and what "before and after" means in the preview. It doesn't add length/format constraints, but the schema already carries those.

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?

Names the precise verb and resource ("Changes what a live AI voice agent says") and enumerates the three editable fields: greeting, system prompt, welcome_instruction. It also states which fields are out of scope and belong to the portal, so an agent can separate this from agent_detail or contact_update 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?

Explicitly states when this tool applies (greeting/system prompt/welcome_instruction) and when it does not (tools, transfers, voice, language, webhooks, audio settings go to the portal). It also prescribes the required two-step dryRun-then-apply workflow, leaving nothing to inference.

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.