Skip to main content
Glama

pulsenetwork

by com.theaslangroupllc.pulse
OverviewDiscussionsAdmin

shopperpulse

ShopperPulse: Birdie, the AI personal shopper — the fleet's shopping meta-agent. POST a shopping list (up to 3 items, free text or structured) and get 3 best-fit picks per item plus a stacked savings plan (loyalty %, coupons, discounted gift cards, right credit card), researched live across findpulse and dealpulse. Best fit to spec wins, not the cheapest listing. The early Birdie gets the deal.

Coverage: Global

Endpoints: • trip ($0.25): Full personal-shopper trip: 3 picks per item + stacked savings plan (POST) • health (FREE): Free liveness + configuration check • recalls ($0.015): Product safety & recall check — official government sources, deterministic • merchant ($0.02): Know Your Merchant (KYM) trust score — deterministic, live public-infrastructure signals

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoProduct name, brand, or category
langNoresponse language
listNoJSON body alternative: free-text shopping list
itemsNoJSON body array, max 3: [{query, budget_usd?, used?, ethical?, local?}]
limitNolimit
sinceNoOnly recalls on/after this date (YYYY-MM-DD)
actionYesWhich endpoint to call. Options: trip | health | recalls | merchant
domainNoMerchant domain or URL (normalized to the host)
countryNoISO-2 country code, or EU for EU/EEA-wide notices

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Which endpoint to call. Options: trip | health"New value: +"Which endpoint to call. Options: trip | health | recalls | merchant"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "trip",
-  "health"
-]New value: +[
+  "trip",
+  "health",
+  "recalls",
+  "merchant"
+]
    • addedInput schema / properties / country
      Added value: +{
+  "description": "ISO-2 country code, or EU for EU/EEA-wide notices",
+  "type": "string"
+}
    • addedInput schema / properties / domain
      Added value: +{
+  "description": "Merchant domain or URL (normalized to the host)",
+  "type": "string"
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "description": "limit",
+  "type": "string"
+}
    • addedInput schema / properties / q
      Added value: +{
+  "description": "Product name, brand, or category",
+  "type": "string"
+}
    • addedInput schema / properties / since
      Added value: +{
+  "description": "Only recalls on/after this date (YYYY-MM-DD)",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Which endpoint to call. Options: trip"New value: +"Which endpoint to call. Options: trip | health"
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "trip"
-]New value: +[
+  "trip",
+  "health"
+]
  3. Added

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries full burden and provides meaningful behavioral details: 'researched live', 'Best fit to spec wins, not the cheapest listing', stacking savings elements, and determinism for recalls/merchant. It also discloses pricing for endpoints. It does not cover failure modes or rate limits, but for a meta-agent the provided behavior context is strong.

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 structured with an intro, coverage line, and endpoint bullets. It front-loads the purpose. However, phrases like 'The early Birdie gets the deal' are filler, and the marketing tone makes it slightly less concise than it could be. Overall, it is organized and mostly informative.

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?

Given four endpoints, no output schema, and no annotations, the description covers each endpoint's purpose and output type (e.g., '3 picks per item + savings plan', 'liveness + configuration check', 'official government sources', 'KYM trust score'). It omits detailed structure of response objects, but for a meta-agent tool with rich description, this is reasonably 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?

Schema coverage is 100% (baseline 3), and the description adds context by mapping the 'action' parameter to endpoint behaviors and explaining the 'list'/'items' free-text vs structured distinction. It also clarifies item limit (3 items) and result shape (3 picks per item), which enriches schema descriptions.

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 clearly states this is 'ShopperPulse: Birdie, the AI personal shopper — the fleet's shopping meta-agent' with specific actions: POST a shopping list and get 3 picks per item plus a savings plan. It distinguishes from sibling tools by positioning itself as a meta-agent that researches across findpulse and dealpulse, and enumerates distinct endpoints (trip, health, recalls, merchant).

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?

The description gives clear context for each endpoint (trip for full shopping, recalls for safety, merchant for trust) and explicitly mentions findpulse and dealpulse as underlying research sources. It implies when to use this meta-agent instead of those direct tools, though it does not explicitly state exclusions or 'use X when...' alternatives.

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

All pulsenetwork 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