Skip to main content
Glama

OpenSwitchboard

by ai.openswitchboard
OverviewDiscussionsAdmin

refine_intent

Give the switchboard your human's OTHER WORDS for something they have already put up, so it can find things worded differently. also_called is up to six short phrases for the same thing — the trade name, the part number, what everyone in that hobby says, "BPK", "die-spring mod" — and not_these is up to six short phrases they say it is NOT ("elastomer kit", "whole pedal set"), which makes close things count for less and hides nothing from them. Use their own words, gathered in ordinary talk: ask what else people call it and whether there is a near neighbour it keeps getting mistaken for. THIS CANNOT CHANGE WHAT THE THING IS — a different thing means taking it down and putting it up again, the same as a different heading. Plain words only: no price, no email address, no phone number, no link, and no wording aimed at an AI, or it comes back with the ordinary plain-words answer. The switchboard looks again by itself the moment this lands, so stay in the conversation and bring your human whoever comes forward. Say the say_note sentence as it stands, and never the id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intent_idYes
not_theseNoShort phrases your human says it is NOT. Up to six. Nothing is hidden from them by this; close things simply count for less.
also_calledNoYour human's other words for the same thing, in their words and in their own language. Up to six short phrases.
identifiersNoThe identifiers for the product or edition, as publish_intent describes them. Sent at all, they replace the ones on the posting, and an empty list takes them off; left out, the ones there stay.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / identifiers
      Added value: +{
+  "description": "The identifiers for the product or edition, as publish_intent describes them. Sent at all, they replace the ones on the posting, and an empty list takes them off; left out, the ones there stay.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "kind": {
+        "description": "What it is, in a few plain words: \"model number\", \"ISBN\", \"catalogue number\".",
+        "maxLength": 40,
+        "minLength": 1,
+        "type": "string"
+      },
+      "value": {
+        "description": "The identifier as printed on the product.",
+        "maxLength": 60,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 3,
+  "type": "array"
+}
    • changedInput schema / required
      Previous value: -[
-  "intent_id",
-  "also_called"
-]New value: +[
+  "intent_id"
+]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full load yet discloses a lot: content restrictions (no price, email, phone, link, or AI-targeted wording, else 'the ordinary plain-words answer'), that the change cannot alter the underlying thing, that not_these hides nothing, and that the system re-searches automatically the moment the call lands. It loses credit for leaning on an unverifiable field ('say the `say_note` sentence as it stands') that appears nowhere in the input schema.

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

Conciseness3/5

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

The purpose is front-loaded in the first clause, but the prose is long, metaphor-saturated, and packs procedural instruction ('stay in the conversation', 'Say the `say_note` sentence as it stands') into a description where it competes with the actual parameter guidance. Several clauses are hard to parse on first read.

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?

For a mutation tool with no output schema and no annotations, it covers the essentials: what is changed, what cannot be changed, side effects (automatic re-lookup), content filters, and post-call behavior. Return shape is only implied indirectly, and the dangling say_note reference slightly undercuts completeness.

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 75%, but the description still adds value beyond it: concrete examples for also_called ('BPK', 'die-spring mod') and not_these ('elastomer kit', 'whole pedal set'), the requirement that phrases be the human's own ordinary words, and the content-class restrictions on phrase values. The identifiers parameter is left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

It conveys that the tool supplies alternate names ('OTHER WORDS') and exclusion phrases for something already listed, and states the scope limit that it cannot change what the thing fundamentally is. However, the heavy metaphor ('switchboard', 'put up', 'taking it down') obscures the operation, and the description makes no attempt to distinguish this from the direct sibling amend_intent — an agent cannot tell from the text why it would refine rather than amend.

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?

It gives a clear when-to-use rule ('Use their own words, gathered in ordinary talk: ask what else people call it and whether there is a near neighbour it keeps getting mistaken for') and an explicit when-not with a redirect ('a different thing means taking it down and putting it up again'). Missing is any named routing to siblings such as amend_intent or publish_intent, so 4 rather than 5.

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

All OpenSwitchboard 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