Sliq

Set Outreach Approval

set_outreach_approval

settings is a partial {subtype: requires_approval} map — True holds the message for the user's approval, False auto-sends. Only the subtypes you name change. Each subtype key names a message type (e.g. email_first_message); an unknown key is rejected with the full valid list.

scope:

'this_agent' (default) — change approval for THIS agent only, leaving the account-wide setting and other agents untouched. Needs an agent in context (or an explicit agent_id). This pins the agent to its own approval settings that no longer follow account-wide changes — tell the user that.
'account' — change the account-wide default that governs every agent with no override of its own. An agent that has its own override is unaffected — warn the user that an account change won't reach any agent that has its own override. Available to the account owner only; when acting for a shared operator, use 'this_agent'.
'inherit_account' — clear THIS agent's own approval settings so it follows the account-wide setting again. settings is ignored.

Returns {success, scope, settings} — settings is the resulting resolved map for the level written. Dict with success, scope, and resulting settings.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`scope`	No	Which level to change. Defaults to 'this_agent'.	this_agent
`agent_id`	No	The agent to change. Defaults to the agent in context.
`settings`	No	Partial map of subtype -> requires_approval. Omit for scope='inherit_account'.
`on_behalf_of`	No	An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

addedInput schema / properties / on_behalf_of

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}

Changed2 schema fields changedSep 23, 2026

addedInput schema / properties / agent_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "The agent to change. Defaults to the agent in context."
+}

removedInput schema / properties / task_id

Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "The agent/task to change. Defaults to the task in context."
-}

First observedSep 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description carries rich behavioral detail: 'this_agent' pins the agent so it no longer follows account-wide changes, 'account' won't reach agents with their own override, 'inherit_account' clears settings and ignores the `settings` arg, and unknown subtype keys are rejected with the full valid list. These are consequential side effects and warnings not derivable from annotations.

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?

The purpose is front-loaded in the summary tag, and the scope bullets are cleanly organized. It is long, but the length is justified by three distinct modes each with non-obvious consequences; there is essentially no filler. Slightly more verbose than strictly necessary for the returns tag.

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 4-param mutation tool with no output schema, the description covers everything an agent needs: the three scope modes and their side effects, parameter semantics, the ignored-arg edge case, and the return shape `{success, scope, settings}`. 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 coverage is 100%, so the baseline is 3. The description nevertheless adds real meaning beyond the schema: it defines `settings` as a partial {subtype: requires_approval} map, explains True=hold/False=auto-send, clarifies only named subtypes change, and expands each scope enum value with its consequences and prerequisites (agent in context or explicit agent_id).

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: 'Change what outbound outreach holds for the user's approval before it sends.' It clearly names the mutation target (outreach-approval settings) and distinguishes itself from the read sibling get_outreach_approval. An agent can tell exactly what this does without opening the 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?

Explicitly says when to call it ('when the user asks to review or auto-send a message type — actually make the change, don't just describe the UI') and gives when-to-use for each scope mode: 'this_agent' for a single agent, 'account' for the account-wide default, 'inherit_account' to clear overrides. It also flags the owner-only restriction and the shared-operator alternative.

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

All Sliq 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?