Skip to main content
Glama

Sliq

by com.getsliq
OverviewDiscussionsAdmin

List Prospect Events

list_prospect_events
Read-only

Spans every campaign by default; pass agent_id to scope to one. To page further back, re-call with before set to the oldest returned event's occurred_at. Dict with count, a summary block (replies_this_week, accepts_this_week, posts_found_this_week, meetings_booked_this_week), and an events array. Events are newest-first; each is {id, kind, channel, owner_email, occurred_at, time_precision, subject_type, snippet, turn, prospect: {id, name, linkedin_url, provider_id, title, company, has_conversation}, agent: {id, title} | null, queued_followup: {...} | null}. turn is 'user' when a draft awaits the user's approval, 'sliq' when a send is queued, else 'none'; queued_followup carries that drafted next step when one exists. prospect.id is null when the event isn't attributable to a tracked row.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindsNoSources to include — any of 'accept', 'linkedin_reply', 'email_reply'. Omit for all three.
limitNoMax events (default 50, capped at 200). Page older with `before`.
beforeNoISO 8601 timestamp cursor; only events strictly older are returned (pass a prior page's oldest `occurred_at`).
agent_idNoScope the events and the summary to one campaign. Omit for the cross-campaign feed. Note `turn` stays prospect-scoped — it can read 'user' off a draft awaiting approval under a different campaign for the same person; `queued_followup` is campaign-matched and won't.
as_teammateNoRead a consented teammate's activity instead of your own — pass their email. Gated on that teammate's conversation-sharing setting; a teammate who hasn't shared is rejected. Omit for your own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Scope the events and the summary to one campaign. Omit for the\ncross-campaign feed. Note `turn` stays prospect-scoped — it can read\n'user' off a draft awaiting approval under a different campaign for\nthe same person; `queued_followup` is campaign-matched and won't."
+}
    • removedInput schema / properties / task_id
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Scope the events and the summary to one campaign. Omit for the\ncross-campaign feed. Note `turn` stays prospect-scoped — it can read\n'user' off a draft awaiting approval under a different campaign for\nthe same person; `queued_followup` is campaign-matched and won't."
-}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only provide readOnlyHint:true, so the description carries the burden of behavioral disclosure. It adds key traits: the feed is newest-first, spans all campaigns by default, supports pagination via `before`, and includes a 7-day summary. It also explains the semantics of `turn` and `queued_followup` in the returns, which goes well beyond a simple read-only hint.

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 description is long but highly structured, with a `<summary>` block and a detailed `<returns>` section. It front-loads the core purpose and usage examples, then follows with pagination and return details. Every sentence contributes value; however, the returns block is dense and could be seen as slightly over-detailed for an initial reading. It earns a 4 rather than 5 because it is not as concise as a two-sentence definition.

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?

With no output schema, the description must explain return values, and it does so thoroughly: count, summary fields, event object structure, and the meaning of `turn` and `queued_followup` are all explained. It also covers pagination (`before`), default scoping, and the null behavior of `prospect.id`. Given the tool's complexityches, this is exceptionally complete.

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?

The input schema already provides 100% coverage of all 5 parameters, so the baseline is 3. The description adds meaningful context beyond the schema for two important parameters: `agent_id` (default scoping to all campaigns) and `before` (pagination technique). It does not redundantly explain every parameter, but the added usage guidance for these two lifts the score above baseline.

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: 'Read the cross-channel prospect activity feed,' and enumerates the exact union of event types (connection accepts, LinkedIn replies, email replies) with accompanying annotations. It differentiates from alternatives by positioning itself as a single call 'instead of stitching the LinkedIn, email, and queue readers together by hand,' which clearly identifies what this tool is not.

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 explicitly states when to use the tool: 'Use it to answer "who replied this week", "what just happened across my campaigns", "who's waiting on me", or "did anyone accept" in one call.' It names the alternative approach ('stitching the LinkedIn, email, and queue readers together by hand'), giving a clear contrast. The scoping and pagination instructions ('pass agent_id to scope to one', 're-call with before set to the oldest returned event's occurred_at') further guide usage.

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