Funkel AI

update_icp

Destructive

Apply an ICP edit (description and/or filters JSON) to one agent. Two-phase: first call returns a confirmation token + preview; the user reviews the diff inline and confirms; second call (with confirmation_token) commits. ALWAYS call draft_icp_edit first so the user sees a before/after; never call update_icp directly without staging a diff. Pre-populate agent_name in the schema args so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

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_icp"
  }
}

Input Schema

Name	Required	Description
`agent_id`	Yes	Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
`agent_name`	No	Agent name (used in the confirm preview)
`icp_filters`	No	New structured filters object. Use company_sizes and exclude_service_providers. excluded_companies accepts exact employer names or LinkedIn company URLs. URLs become slug names and remain separately in competitor_urls. Ask the user to verify the employer name. Omit to leave unchanged.
`icp_description`	No	New free-text ICP description (omit to leave unchanged)
`industry_inputs`	No	Explicit raw industry intent from draft_icp_edit ready_to_execute_args. Omit for canonical-only edits. Nested old metadata cannot restore removed raw intent.
`confirmation_token`	No	Phase-2 token (omit on phase-1)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 16, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing the two-phase confirmation-token protocol, the inline diff preview, and the confirm step, and by explaining the MCP-transport override. Annotations already flag destructiveHint=true / idempotentHint=false, so the added workflow context is real value, though it never states what is destroyed or how partial edits interact with destructive replacement.

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 purpose and the phase flow, and every sentence is substantive. The trailing MCP-transport sentence is short but introduces ambiguity that briefly forces the reader to re-interpret the earlier imperative, costing a point.

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?

Covers the mutation workflow, confirmation semantics, and the draft-first prerequisite for a 6-parameter tool with no output schema, so an agent has enough to call it correctly. It falls short of 5 only because it does not state what happens to unmentioned fields beyond the schema's 'omit to leave unchanged' notes, nor clarify which mode takes precedence in a given session.

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 adds genuine meaning: it explains that agent_name should be pre-populated 'so the preview is human-readable' and clarifies the two-phase role of confirmation_token. That is useful guidance beyond the schema's own descriptions.

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 and resource ('Apply an ICP edit (description and/or filters JSON) to one agent') and immediately distinguishes itself from the sibling draft_icp_edit by role. An agent can tell what this tool does and how it differs from the draft/preview tool without opening either schema.

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 explicit when-to-use and when-not: 'ALWAYS call draft_icp_edit first so the user sees a before/after; never call update_icp directly without staging a diff,' and names the phase-2 trigger (confirmation_token). The only flaw is the closing MCP clause ('call this tool once... It runs right away'), which sits in tension with the 'ALWAYS/never' instruction and leaves the agent to reconcile the two modes.

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

All Funkel AI 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.

Resources

Need Help?