Anyreach

Run a create operation

call_create_tool

Invoke an Anyreach operation that adds something new — an agent, a draft version, a knowledge base or source, a widget, a workflow — without overwriting or removing anything that exists. Each operation's risk and call_with (from search_tools or describe_tool) name the one call tool that runs it; the others refuse it. organization_id is the Anyreach organization to act on behalf of — most operations are organization-scoped. You may omit it: if the user belongs to exactly one organization it is used automatically, and if they belong to several the call is refused with the list, so ask which one and retry. arguments must conform to the operation's inputSchema. Returns the upstream JSON response.

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": {
      "name": "<name>"
    },
    "name": "call_create_tool"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`arguments`	No
`organization_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare non-readonly, non-destructive, non-idempotent, and closed-world, and the description is consistent with them ('adds something new ... without overwriting'). It adds real value annotations cannot: org resolution fallback behavior, the refusal semantics when multiple orgs match, and the fact that the upstream JSON response is returned verbatim. It does not discuss idempotency or repeat-call effects, which leaves a small gap.

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 core scope statement, then routing, then parameter behavior, then return value — a sensible order with no filler. The opening sentence is long and em-dash-heavy, but every clause carries distinct information.

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?

This is a generic pass-through dispatcher with a weak schema (0% coverage) and no output schema, and the description compensates on every axis an agent needs: which operation belongs here, how to discover the correct call tool, how organization scoping resolves, argument conformance, and what is returned. Nothing material is missing.

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 0%, so the description must carry the load. It fully explains `organization_id` (auto-selected for single-org users, refused with a list otherwise) and clarifies that `arguments` must conform to the target operation's inputSchema. `name` is only implicitly framed as the operation identifier via the search_tools/describe_tool routing sentence, so it is not spelled out directly.

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 concrete verb (invoke an Anyreach operation) plus the resource class, and enumerates examples (agent, draft version, knowledge base, widget, workflow). The clause 'without overwriting or removing anything that exists' sharply separates it from call_change_tool and call_read_tool, so an agent can pick the right call tool without opening schemas.

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?

Explicit routing rule: each operation's `risk` and `call_with` (obtained from search_tools or describe_tool) identify the single call tool that will accept it, and 'the others refuse it.' It also gives concrete when-to-omit guidance for organization_id, including the multi-org refusal-and-retry path.

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

All Anyreach 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?