Sliq

Query prospect research

query_prospect_research

Read-only

Call this BEFORE researching a lead to avoid re-doing work (and re-spending credits), or to reference prior findings in a follow-up, or to answer "what did you find about X?". Dict with count, truncated, and items array (each row {id, agent_id, person_linkedin_slug, person_linkedin_pid, person_email, subject_kind, company_domain, display_name, content, url, source, created_at}).

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": "query_prospect_research"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max findings to return (default 50, newest first).
`offset`	No	Number of findings to skip, for paging past `limit`.
`person`	No	A lead handle (linkedin_slug / linkedin_provider_id / email) to get just that lead's findings; omit for all research on the agent.
`agent_id`	Yes	The agent whose saved research to read.
`on_behalf_of`	No	A teammate's email, or an agency client's from list_agency_clients, to run this call in that 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 changedNov 6, 2026

changedInput schema / properties / on_behalf_of / description

Previous value: -"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."New value: +"A teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."

Changed2 schema fields changedNov 5, 2026

changedInput schema / properties / person / anyOf

Previous value: -[
-  {
-    "description": "A handle to a prospect/lead. The agent passes the identifiers it already\nholds; the tool canonicalizes server-side. The agent must NOT hand-type a\ncanonical identifier — pass the URL / provider id / email it was given.",
-    "properties": {
-      "display_name": {
-        "default": "",
-        "description": "Human-readable name for the UI label.",
-        "type": "string"
-      },
-      "email": {
-        "default": "",
-        "description": "The lead's email, if that's the only identifier.",
-        "type": "string"
-      },
-      "linkedin_provider_id": {
-        "default": "",
-        "description": "The lead's LinkedIn provider id (ACoAA…), if known.",
-        "type": "string"
-      },
-      "linkedin_url": {
-        "default": "",
-        "description": "The lead's LinkedIn profile URL, if known.",
-        "type": "string"
-      }
-    },
-    "title": "PersonRef",
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "A handle to a prospect/lead. Copy each identifier verbatim from the tool result\nthat surfaced the person; the tool canonicalizes it.",
+    "properties": {
+      "display_name": {
+        "default": "",
+        "description": "Human-readable name for the UI label.",
+        "type": "string"
+      },
+      "email": {
+        "default": "",
+        "description": "The lead's email, if that's the only identifier.",
+        "type": "string"
+      },
+      "linkedin_provider_id": {
+        "default": "",
+        "description": "The lead's LinkedIn provider id (ACoAA…), if known.",
+        "type": "string"
+      },
+      "linkedin_slug": {
+        "default": "",
+        "description": "The lead's LinkedIn profile slug or profile URL, if known.",
+        "type": "string"
+      }
+    },
+    "title": "PersonRef",
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / person / description

Previous value: -"A lead handle (linkedin_url / linkedin_provider_id / email) to\nget just that lead's findings; omit for all research on the agent."New value: +"A lead handle (linkedin_slug / linkedin_provider_id / email) to\nget just that lead's findings; omit for all research on the agent."

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."
+}

Changed4 schema fields changedSep 23, 2026

addedInput schema / properties / agent_id

Added value: +{
+  "description": "The agent whose saved research to read.",
+  "type": "integer"
+}

changedInput schema / properties / person / description

Previous value: -"A lead handle (linkedin_url / linkedin_provider_id / email) to\nget just that lead's findings; omit for all research on the task."New value: +"A lead handle (linkedin_url / linkedin_provider_id / email) to\nget just that lead's findings; omit for all research on the agent."

removedInput schema / properties / task_id

Removed value: -{
-  "description": "The task whose saved research to read.",
-  "type": "integer"
-}

changedInput schema / required

Previous value: -[
-  "task_id"
-]New value: +[
+  "agent_id"
+]

First observedSep 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds value by disclosing the credit-saving rationale and the exact return shape (count, truncated, items). Minor gap: it does not mention paging interaction with `limit`/`offset` or ordering in prose, though the schema covers that.

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?

Front-loaded summary followed by a returns block; every sentence (especially the pre-research cost warning) earns its place. The XML tag structure makes the purpose and return contract scannable with no filler.

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?

No output schema exists, but the description supplies the return contract (dict with count, truncated, items and field list), which is exactly what's needed. It does not explain what `truncated` implies for paging, a small remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (limit, offset, person, agent_id, on_behalf_of) is already documented. The description adds no parameter-level meaning beyond what the schema provides, so baseline 3 applies.

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: 'Read back personalization research already saved for an agent.' Clearly the read counterpart to save_prospect_research, and the 'read back ... already saved' phrasing distinguishes it from research-generation tools in the sibling list.

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?

Gives explicit when-to-use conditions: call BEFORE researching to avoid re-doing work and re-spending credits, to reference prior findings in a follow-up, or to answer 'what did you find about X?'. The credit-cost framing gives a concrete reason to prefer this over re-running enrichment.

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?