Skip to main content
Glama
Sign In

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Save prospect research

save_prospect_research

Call this after you synthesize a "why I'm reaching out" angle for a recipient — once per recipient, batching all of that person's findings (and you may batch across recipients). Each finding is YOUR synthesized insight ("former Stripe PM, just posted about scaling support"), NOT raw scraped post text or an article abstract.

Pass the lead in each finding's person. A company finding (subject_kind='company') still attaches to the person it personalizes; set company_domain to record the company. Dict with created (the count of saved research rows).

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>",
      "findings": "<findings>"
    },
    "name": "save_prospect_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idYesThe agent these findings belong to.
findingsYesOne ProspectFinding per synthesized insight; each carries the lead handle it personalizes, its subject_kind, and the source.
on_behalf_ofNoA 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.

  1. Changed1 schema field changed
    • 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."
  2. Changed2 schema fields changed
    • addedInput schema / properties / findings / items / properties / person / properties / linkedin_slug
      Added value: +{
+  "default": "",
+  "description": "The lead's LinkedIn profile slug or profile URL, if known.",
+  "type": "string"
+}
    • removedInput schema / properties / findings / items / properties / person / properties / linkedin_url
      Removed value: -{
-  "default": "",
-  "description": "The lead's LinkedIn profile URL, if known.",
-  "type": "string"
-}
  3. Changed2 schema fields changed
    • addedInput schema / properties / findings / items / properties / subject_kind / title
      Added value: +"EntityType"
    • 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."
+}
  4. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "The agent these findings belong to.",
+  "type": "integer"
+}
    • removedInput schema / properties / task_id
      Removed value: -{
-  "description": "The task these findings belong to.",
-  "type": "integer"
-}
    • changedInput schema / required
      Previous value: -[
-  "task_id",
-  "findings"
-]New value: +[
+  "agent_id",
+  "findings"
+]
  5. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real context beyond that — the write is user-visible on the agent page, findings are batched per recipient, and a company finding still attaches to the person with company_domain recorded. However, for a persistence tool it omits a critical behavior: whether re-saving the same person/finding creates duplicate rows or overwrites, and what happens on invalid person refs.

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?

Purpose is front-loaded in sentence one, with usage, content constraints, and the returns note following in a logical order and no filler. The summary/returns markup is slightly heavy for the amount of content but nothing is redundant.

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?

For a 3-parameter write tool with no output schema, the description covers purpose, timing, batching, content requirements, the person/company relationship, and the return shape ('Dict with created'). The remaining gap is duplicate/idempotency behavior and any precondition that the agent must already exist.

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 the structured schema already explains agent_id, findings, person sub-fields, source enum and company_domain. The description does add one genuinely useful relationship hint (company findings still attach via person, with company_domain recording the company), but the statement 'Pass the lead in each finding's person' largely restates the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb+resource: 'Persist synthesized personalization research for leads on an agent,' and even explains the downstream effect ('what Sliq found' on the agent page). It is unmistakably distinct from the read-side sibling query_prospect_research in substance, though it never names that sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong when-to-use guidance: 'Call this after you synthesize a "why I'm reaching out" angle... once per recipient, batching all of that person's findings (and you may batch across recipients),' plus an explicit exclusion ('NOT raw scraped post text or an article abstract'). It stops short of naming any alternative tool (e.g. query_prospect_research or append_learning) or stating when not to call it.

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

All Sliq toolsInspect
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