Skip to main content
Glama
Sign In

Sliq

by com.getsliq
OverviewDiscussionsAdmin

Matches ICP

matches_icp
Read-only

Runs the two mechanical checks — employee-count band and funding-stage normalized membership, both include-on-null — and combines them with the caller's industry and location judgments. Industry fit and location are NOT decided here: the agent judges both and passes its verdicts in. {passed, location_ok, size_ok, size_null_included, size_contested, industry_ok, funding_stage_ok, funding_stage_null_included}. passed is the AND of location_ok, size_ok, industry_ok, funding_stage_ok.

Size is not a pure hard gate — it includes-on-uncertain-data like funding, because Apollo undercounts privately-held / industrial firms:

  • size_null_included True → Apollo had no headcount; included anyway.

  • size_contested True → Apollo's count is below the smallest band floor (probably an undercount); included anyway. Either flag → score that Company-size evaluation 5 (amber "verify"), not

  1. A count in a gap between bands or above the ceiling is a confident mismatch → size_ok False (drop). Score Industry from industry_verdict (fit → 10, uncertain → 5) and Location from location_verdict (in → 10, uncertain → 5).

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": {
      "industry_verdict": "<industry_verdict>",
      "location_verdict": "<location_verdict>",
      "icp_employee_count_ranges": "<icp_employee_count_ranges>"
    },
    "name": "matches_icp"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
employee_countNoCandidate headcount. None when unknown.
industry_verdictYesThe agent's industry judgment — 'fit' (confidently in an ICP industry), 'uncertain' (plausibly in, but signals thin or conflicting — kept and flagged), or 'off' (drop).
location_verdictYesThe agent's judgment of whether the candidate's HQ lies within the configured ICP locations — 'in', 'uncertain' (plausibly in, but the location data is partial or it sits just outside a listed place — kept and flagged), or 'out' (drop).
icp_funding_stagesNoConfigured funding stages — optional; unset or empty makes the funding check a no-op (everything passes it).
latest_funding_stageNoApollo's title-case stage string ('Series B', 'Seed'); None/absent under patchy coverage.
icp_employee_count_rangesYesConfigured size ranges, each a 'min,max' pair ('25,200'), an empty side meaning unbounded ('500,', ',50').

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. Changed1 schema field changed
    • 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."
+}
  3. Changed4 schema fields changed
    • removedInput schema / properties / icp_locations
      Removed value: -{
-  "description": "Configured ICP location strings.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}
    • removedInput schema / properties / location
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Candidate location (Apollo enriched.location, or TheirStack\ncity/country). None when enrichment had none."
-}
    • addedInput schema / properties / location_verdict
      Added value: +{
+  "description": "The agent's judgment of whether the candidate's HQ lies\nwithin the configured ICP locations — 'in', 'uncertain' (plausibly\nin, but the location data is partial or it sits just outside a listed\nplace — kept and flagged), or 'out' (drop).",
+  "enum": [
+    "in",
+    "uncertain",
+    "out"
+  ],
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "industry_verdict",
-  "icp_locations",
-  "icp_employee_count_ranges"
-]New value: +[
+  "industry_verdict",
+  "location_verdict",
+  "icp_employee_count_ranges"
+]
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true; the description adds substantial behavioral context beyond that — that `passed` is the AND of four sub-verdicts, that size and funding are include-on-null rather than hard gates, why (Apollo undercounts private/industrial firms), and how contested counts become amber rather than hard drops. This is exactly the kind of computation semantics an agent cannot infer from the schema.

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?

Well front-loaded with a summary block stating the gate's role before detail, and the returns block is necessary because there is no output schema. A few downstream scoring instructions ('score size 5 amber, not 10') are dense and could be trimmed, but they carry decision-relevant meaning rather than filler.

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 fully documents the returned fields (`passed`, the four *_ok booleans, and the two inclusion flags), which is the critical gap it must cover. Given seven parameters and a non-obvious include-on-null policy, the definition supplies everything needed to call it correctly and interpret the result.

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, but the description earns more by explaining derived behavior rather than restating fields: that `size_null_included` and `size_contested` derive from `employee_count` undercount assumptions, that an unset funding-stage list makes that check a no-op, and that gap/above-ceiling counts are confident mismatches. It adds real meaning over the schema's field-level text.

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+resource+scope: a per-candidate ICP gate for find-companies News mode that runs the two mechanical checks (employee-count band, funding-stage membership) and ANDs them with caller-supplied verdicts. It clearly delineates what the tool does NOT decide (industry, location), which distinguishes it from any judgment-oriented sibling.

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?

Explicitly sets the division of labor: the agent judges industry and location and passes verdicts in, while size and funding are computed here. Usage is scoped to 'find-companies News mode', which tells the agent where it belongs. It stops short of naming a specific alternative tool to use when not in News mode, so it is clear-context rather than full when/when-not routing.

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