Skip to main content
Glama
Coval MCP Server

Coval MCP Server

Official
by coval-ai

Update agent

update_agent
Destructive

Modify an existing agent's configuration by changing only the fields you provide, including prompt, endpoint, metadata, display name, or phone number.

Instructions

Update an existing agent configuration. Only provided fields are changed.

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": "update_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptNoNew system prompt
agent_idYesThe unique ID of the agent to update
endpointNoNew endpoint URL
metadataNoNew metadata
display_nameNoNew display name
phone_numberNoNew phone number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / metadata / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description doesn't need to repeat the write/destructive nature. It does add genuinely useful patch semantics ("Only provided fields are changed"), which is not derivable from annotations. However, it says nothing about what destruction means in practice (e.g., a prompt overwrite being irreversible) or what happens if agent_id doesn't exist.

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?

Two short sentences, zero filler, with the core action front-loaded and the partial-update constraint immediately after. Nothing could be removed without losing information.

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?

With full schema coverage and no output schema, the description covers the mechanics adequately. But for a tool flagged destructive, it omits what an agent most needs to know before calling: whether the update is reversible, whether the agent must be idle, and how invalid IDs or validation failures are surfaced.

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 description coverage is 100%, so the baseline would be 3. The description earns above baseline by clarifying that omitted optional fields are left untouched, which is a real semantic about how the six parameters are interpreted together and isn't stated in the schema.

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?

States a specific verb+resource: "Update an existing agent configuration." An agent can immediately distinguish this from create_agent, get_agent, and list_agents without opening the schema. No explicit sibling naming, but the intent is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by "existing agent" (the agent must already exist, so use create_agent otherwise), but no when-to-use/when-not guidance or alternatives are named. The agent has to infer the create-vs-update split from sibling names alone.

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