Skip to main content
Glama

Connections

by icu.connections
OverviewDiscussionsAdmin

How do I... - find the right Connections tool for a task

connections_help
Read-only

Use this BEFORE guessing which Connections tool to call, or when unsure what Connections can do at all. Pass intent in the member's own words ('create an event', 'my todos', 'post a deal', 'remember this', 'who do i know') and get back the ONE tool to call: its required fields, optional fields, a runnable example, and whether it needs confirmation before calling. Add domain to disambiguate when the intent alone could mean more than one thing. With no intent, or one that matches nothing, returns the full capability map instead: every domain Connections covers, its canonical read tool and write tool, one line each - the answer to 'what can you do'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoAlias for `intent`.
queryNoAlias for `intent`.
domainNoOptional: narrow matching to one domain when intent alone is ambiguous (e.g. 'add' could be a todo or a contact).
intentNoWhat the member wants to do, in plain words (e.g. 'create an event', 'my todos', 'remember this'). Omit for the full capability map. `question`, `query` and `q` are accepted aliases; any OTHER argument name is reported back in `ignored_params` rather than silently dropped.
questionNoAlias for `intent` - this tool's title invites it, so it is accepted rather than discarded.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / domain / enum
      Previous value: -[
-  "contacts",
-  "todos",
-  "events",
-  "deals",
-  "email",
-  "notes",
-  "memory",
-  "workspace"
-]New value: +[
+  "contacts",
+  "todos",
+  "calendar",
+  "events",
+  "deals",
+  "email",
+  "notes",
+  "memory",
+  "workspace"
+]
  2. Changed1 schema field changed
    • changedInput schema / properties / domain / enum
      Previous value: -[
-  "contacts",
-  "todos",
-  "events",
-  "deals",
-  "notes",
-  "memory",
-  "workspace"
-]New value: +[
+  "contacts",
+  "todos",
+  "events",
+  "deals",
+  "email",
+  "notes",
+  "memory",
+  "workspace"
+]
  3. Changed5 schema fields changed
    • changedInput schema / properties / intent / description
      Previous value: -"What the member wants to do, in plain words (e.g. 'create an event', 'my todos', 'remember this'). Omit for the full capability map."New value: +"What the member wants to do, in plain words (e.g. 'create an event', 'my todos', 'remember this'). Omit for the full capability map. `question`, `query` and `q` are accepted aliases; any OTHER argument name is reported back in `ignored_params` rather than silently dropped."
    • addedInput schema / properties / q
      Added value: +{
+  "description": "Alias for `intent`.",
+  "type": "string"
+}
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Alias for `intent`.",
+  "type": "string"
+}
    • addedInput schema / properties / question
      Added value: +{
+  "description": "Alias for `intent` - this tool's title invites it, so it is accepted rather than discarded.",
+  "type": "string"
+}
    • addedInput schema / required
      Added value: +[]
  4. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare the tool read-only and non-destructive; the description adds return-behavior context beyond annotations—returning a single recommended tool with fields/example/confirmation, or the full capability map with no intent. It is transparent about the no-intent fallback, though it does not detail response structure or edge cases beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences front-load the primary usage directive and keep every clause informative. Examples are compact, and the description does not restate schema fields or annotations.

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?

For a routing/help tool with no output schema, the description covers all call modes—intent, domain, and omitted intent—plus the shape of both possible outputs. An agent has enough information to invoke it correctly without needing additional documentation.

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 descriptions cover all five parameters, and the description builds on them by explaining intent semantics ('in the member's own words'), the disambiguation role of `domain`, and the alias/ignored_params behavior. This adds value beyond the schema, so it earns above the baseline 3.

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 an explicit directive—'Use this BEFORE guessing which Connections tool to call'—and clearly identifies the resource (the Connections toolset) and the concrete output (the ONE tool to call, its fields, example, and confirmation requirement). This distinguishes the meta-routing helper from operation siblings like connections_todo_add or connections_event_create.

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 gives explicit when-to-use conditions ('BEFORE guessing', 'when unsure what Connections can do at all') and describes the fallback: no intent or unmatched intent returns the full capability map. It also instructs when to add `domain` to disambiguate, making the selection rule actionable.

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

All Connections 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