Sliq

Request User Action

request_user_action

Prefer on-platform tools when the channel is automatable: setup_linkedin_sequence for LinkedIn DMs and connection requests, the email tools (draft_email, setup_email_sequence) for email outreach, find_email for contact lookups. Use this tool only after ruling those out.

This tool is for a one-off ask about a particular prospect. When the off-platform step is a step of a sequenced campaign — every prospect reaching that point gets it, and the campaign continues once it's done — author a manual node in define_sequence instead: entry queues the same row, and marking it done advances the prospect onto the node's next step.

Dedup is per pending row on (agent, prospect, bucket_name): if the same prospect already has a pending row for the same bucket the tool returns created=False with the existing row's bucket and action_description so you can see what's already queued. Re-flagging the same prospect for a different bucket is allowed; re-flagging after the user marks a prior row done or dismisses it is also allowed. Dict with created (bool), action_id (int or None), id (int), and reason (str).

Input Schema

TableJSON Schema

Name	Required	Description
`agent_id`	Yes	ID of the campaign agent this request belongs to.
`bucket_name`	Yes	Short user-facing label naming the ask (e.g. "voice-note", "founder-gift"). Shown in the Slack DM and home-page row. Also the third dimension of the pending-dedup key — two different buckets can coexist as pending rows on the same prospect.
`prospect_id`	Yes	The prospect's `id` — the outreach_prospects primary key, as returned on every query_prospects row.
`action_description`	Yes	One-line description of what the user should do.
`completion_criteria`	No	How the agent should advance the prospect after the user sends an update about what they did.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 23, 2026

addedInput schema / properties / agent_id

Added value: +{
+  "description": "ID of the campaign agent this request belongs to.",
+  "type": "integer"
+}

removedInput schema / properties / task_id

Removed value: -{
-  "description": "ID of the campaign task this request belongs to.",
-  "type": "integer"
-}

changedInput schema / required

Previous value: -[
-  "task_id",
-  "prospect_id",
-  "bucket_name",
-  "action_description"
-]New value: +[
+  "agent_id",
+  "prospect_id",
+  "bucket_name",
+  "action_description"
+]

First observedSep 15, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only state readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden. It expands significantly by explaining dedup semantics on `(agent, prospect, bucket_name)`, the `created=False` return path with existing row details, and when re-flagging is or is not allowed. This is rich, non-obvious behavior disclosed clearly.

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?

The description is long but every section earns its place: core action, canonical examples, exclusions/alternatives, sequencing distinction, dedup rules, and return shape. It is front-loaded with the most important information and uses clear structural markers (`<summary>`, `<returns>`).

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?

Given there is no output schema, the description compensates by stating the exact return fields. It covers selection criteria, exclusions, dedup edge cases, and parameter semantics. An agent has enough context to decide when to call this tool and to interpret its response without additional documentation.

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% with already-detailed parameter descriptions, so the baseline is 3. The description adds value above the schema by explaining `bucket_name`'s role as a dedup key and UI label, and by noting that `action_description` is included when a duplicate is detected. It does not add much for `completion_criteria`, but the schema handles that parameter adequately.

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 specific verb and resource: 'Flag a prospect for the user to act on directly.' It clearly distinguishes itself from sibling tools by contrasting with `setup_linkedin_sequence`, email tools, `find_email`, and `define_sequence`, so an agent can tell exactly what this tool is for.

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?

The description gives explicit when-to-use and when-not-to-use guidance: use for off-platform or human-judgment asks, 'only after ruling out' on-platform alternatives, and use `define_sequence` with a `manual` node for sequenced campaign steps. This is detailed routing guidance that leaves little to inference.

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?