Skip to main content
Glama

AINDEX

Change an agent's name, strategy or schedule

update_agent
Idempotent

Change what an agent is called, its strategy (its instructions, in the owner's words) or how often it checks. Limits, the model and anything about money stay on the website. Confirm the new strategy with the person before sending it. Needs a sign-in that may run agents.

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": "<agent>"
    },
    "name": "update_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
agentYes
webhookNoA public https URL pinged when something happens to the agent (a wake condition, a trade, a stop); the ping carries no data, read get_agent_feed. null removes it.
strategyNo
every_minutesNoMinutes between checks; null for no schedule (only when woken).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare a non-read-only, non-destructive, idempotent write, so the description's added value is the auth requirement and the human-confirmation step before sending a strategy. It does not disclose partial-update semantics — whether omitted fields like webhook or every_minutes are left untouched — which matters most for a five-parameter update with only one required field.

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?

Four short sentences, purpose front-loaded, and each sentence carries distinct information (scope, exclusions, safety step, auth). The register drifts slightly ('anything about money stay on the website'), a minor blemish in an otherwise tight definition.

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?

For a mutation tool with no output schema and thin parameter documentation, the definition covers what can and cannot be changed, the confirmation requirement, and the auth need. The remaining gap is merge versus replace behavior on a partially supplied payload, which an agent would still have to infer.

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 coverage is only 40%, and the description compensates for the most consequential field by glossing strategy as 'its instructions, in the owner's words', which explains the 4000-char allowance. Name and every_minutes are restated in plain terms, but the agent identifier and webhook receive no help in the description beyond what the schema already provides.

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 (change) and names the three mutable resources: the agent's display name, its strategy, and its check frequency. It also explicitly excludes limits, model and money, which routes the agent away from this tool for those concerns rather than leaving the boundary implicit.

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?

Gives clear when-to-use scope and a when-not condition ('Limits, the model and anything about money stay on the website'), plus prerequisites (sign-in that may run agents, confirm the strategy with the person). It stops short of naming a sibling for scheduling changes even though schedule_checks exists, so the overlap on 'how often it checks' is left for the agent to resolve.

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.

Resources