Skip to main content
Glama

workspace-alberta

by io.github.HarleyCoops
OverviewDiscussionsAdmin

Match procurement opportunities to my business

find_matching_opportunities
Read-only

Rank CanadaBuys and Alberta APC opportunities against a business profile. Pass an inline profile to describe the business per call. When configured, search terms or business capabilities may be sent to Cohere to select commodity filters. See /privacy.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoOnly show opportunities closing within N days (default 60)
limitNoMaximum opportunities to return (default 15, max 30)
profileNoInline business profile used for this call only. Overrides any saved profile. On the shared public endpoint without a subscriber key, this is the way to describe your business.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNo
countNo
matchesNo
warningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / matches / items / properties / closes_at
      Added value: +{
+  "description": "Closing time as ISO 8601 in Alberta time with UTC offset; empty when unknown",
+  "type": "string"
+}
    • addedOutput schema / properties / matches / items / properties / closing / description
      Added value: +"Closing value exactly as the source published it"
    • addedOutput schema / properties / matches / items / properties / days_until / description
      Added value: +"Calendar days to the closing date in Alberta time; 0 means it closes today"
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "type": "integer"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "matches": {
+      "items": {
+        "properties": {
+          "buyer": {
+            "type": "string"
+          },
+          "category": {
+            "type": "string"
+          },
+          "closing": {
+            "type": "string"
+          },
+          "days_until": {
+            "type": [
+              "integer",
+              "null"
+            ]
+          },
+          "reasons": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "reference": {
+            "type": "string"
+          },
+          "region": {
+            "type": "string"
+          },
+          "score": {
+            "type": "integer"
+          },
+          "solicitation": {
+            "type": "string"
+          },
+          "source": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "warnings": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), but the description adds real behavioral context beyond them: it discloses that search terms/business capabilities may be transmitted to Cohere and points to /privacy. This third-party data-sharing note is meaningful and not present in the structured fields, though ranking behavior is still unexplained.

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?

Three short sentences, purpose front-loaded, no filler. The closing 'See /privacy' is a slightly dangling reference but still earns its place as a pointer to the disclosure it summarizes.

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?

An output schema exists, so return-value explanation is unnecessary, and the nested profile object is fully documented in the schema. The description covers purpose, the inline-profile mechanism, and the privacy implication; only the ranking method and the relation to saved-profile tools are left implicit, which is a minor gap for this complexity.

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%, including the nested profile fields (location, industries, description, capabilities, company_name) and the day/limit defaults, so the schema does the heavy lifting. The description only adds that the profile is inline and per-call, which the schema already states, so baseline 3 is correct.

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?

States a specific verb and resource ('Rank ... opportunities against a business profile') and names the two data sources (CanadaBuys, Alberta APC). It is distinguishable from generic siblings like search_opportunities or find_opportunities by being profile-driven ranking, though it never explicitly contrasts itself with them.

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

Usage Guidelines3/5

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

The description tells the agent to pass an inline `profile` per call, implying usage when no saved profile exists, but it gives no explicit when-to-use/when-not guidance and never names a sibling alternative (e.g., why use this instead of find_opportunities or set_business_profile first). Usage is only implied.

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

All workspace-alberta 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