Skip to main content
Glama

federation_act

Destructive

Invoke any served tool through the root surface, for clients that only call tools in their own tools/list (CO 525, CO 529). BRANCHED platform tools: tenant_id + tool + arguments; names from federation_enter_tenant's platform_tools, schemas from federation_help {"tenant_id":"","tool_defs":""}. UNLISTED root tools: tool + arguments, no tenant_id; names + schemas from federation_help {"tool_defs":"all"}. Authorization is decided per inner tool exactly as a direct call: scope, tenant ownership and pricing apply unchanged — reach, never authority. Refusals: act_recursion, tenant_id_required, tenant_id_not_applicable, unknown_tool. For reads, prefer federation_read: clients can allow it once. Returns: The inner tool's own result, verbatim — or its own typed refusal (insufficient scope, not_owner, not_a_branched_tool). Example: call federation_act with arguments {"tenant_id":"<tenant_id>","tool":""}.

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": {
      "tool": "<tool>"
    },
    "name": "federation_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYesA branched platform tool (e.g. 'booking_status') or an unlisted root tool; names and schemas from federation_help with tool_defs.
argumentsNoThe inner tool's own arguments, exactly as its schema defines them.
tenant_idNoREQUIRED for a branched platform tool: the tenant that serves it (from federation_enter_tenant). OMIT for a root tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / tenant_id / description
      Previous value: -"REQUIRED for branched platform tools: the tenant whose composed surface serves the tool (from federation_list_tenants / federation_enter_tenant). OMIT for root tools."New value: +"REQUIRED for a branched platform tool: the tenant that serves it (from federation_enter_tenant). OMIT for a root tool."
    • changedInput schema / properties / tool / description
      Previous value: -"The tool to invoke: a branched platform tool (names from federation_enter_tenant's platform_tools, schemas from federation_help with tenant_id + tool_defs, e.g. 'booking_status') or an unlisted root tool (names/schemas from federation_help with tool_defs)."New value: +"A branched platform tool (e.g. 'booking_status') or an unlisted root tool; names and schemas from federation_help with tool_defs."
  2. Changed1 schema field changed
    • changedInput schema / properties / tool / description
      Previous value: -"The tool to invoke: a branched platform tool (names/schemas from federation_enter_tenant's platform_tool_defs, e.g. 'booking_status') or an unlisted root tool (names/schemas from federation_help with tool_defs)."New value: +"The tool to invoke: a branched platform tool (names from federation_enter_tenant's platform_tools, schemas from federation_help with tenant_id + tool_defs, e.g. 'booking_status') or an unlisted root tool (names/schemas from federation_help with tool_defs)."
  3. Changed3 schema fields changed
    • changedInput schema / properties / tenant_id / description
      Previous value: -"The tenant whose composed surface serves the tool (from federation_list_tenants / federation_enter_tenant)."New value: +"REQUIRED for branched platform tools: the tenant whose composed surface serves the tool (from federation_list_tenants / federation_enter_tenant). OMIT for root tools."
    • changedInput schema / properties / tool / description
      Previous value: -"The branched platform tool to invoke (e.g. 'booking_status', 'workflow_run') — names and schemas come from federation_enter_tenant's platform_tool_defs."New value: +"The tool to invoke: a branched platform tool (names/schemas from federation_enter_tenant's platform_tool_defs, e.g. 'booking_status') or an unlisted root tool (names/schemas from federation_help with tool_defs)."
    • changedInput schema / required
      Previous value: -[
      -  "tenant_id",
      -  "tool"
      -]New value: +[
      +  "tool"
      +]
  4. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses the authorization model — 'Authorization is decided per inner tool exactly as a direct call: scope, tenant ownership and pricing apply unchanged — reach, never authority' — which tells an agent that this wrapper cannot escalate privilege. It also enumerates concrete refusal codes (act_recursion, tenant_id_required, tenant_id_not_applicable, unknown_tool) and states that the inner tool's own typed refusals (insufficient scope, not_owner, not_a_branched_tool) pass through, giving an agent the failure surface it needs for error handling. No contradiction with the destructiveHint=true annotation, since the tool can dispatch arbitrary inner tools.

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?

It is dense but front-loaded, with useful typographic markers (BRANCHED / UNLISTED / Refusals / Returns) that let an agent scan to the relevant branch. Minor waste exists: the internal ticket references '(CO 525, CO 529)' carry no meaning for a caller, and the trailing example restates the schema-visible argument shape rather than adding a non-obvious case.

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?

For a three-parameter dispatcher with a nested free-form arguments object and no output schema, the description covers what an agent needs: the two invocation modes, prerequisite discovery tools, the authorization pass-through rule, enumerated refusal codes, and the fact that the inner tool's result is returned verbatim. Nothing material is left to inference.

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 would be 3, but the description adds orchestration meaning the schema does not: where tool names come from (federation_enter_tenant's platform_tools for branched tools, federation_help {"tool_defs":"all"} for root tools) and where argument schemas come from (federation_help {tenant_id, tool_defs}). The rule that tenant_id is included for branched tools and omitted for root tools is stated in both places, but the discovery sequencing is genuinely additive.

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?

The description opens with a precise verb and resource — 'Invoke any served tool through the root surface' — and immediately scopes it to 'clients that only call tools in their own tools/list'. It then splits the tool's two operating modes (BRANCHED platform tools vs UNLISTED root tools) and distinguishes itself from federation_read for reads, so an agent can identify both purpose and sibling boundary 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?

It states explicitly when this tool applies (list-gated clients), when each branch applies (tenant_id present for branched tools, omitted for root tools), and names the preferred alternative — 'For reads, prefer federation_read: clients can allow it once.' It also routes discovery to federation_enter_tenant and federation_help, which is actionable when/when-not guidance rather than an implied hint.

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