Skip to main content
Glama

OpenSwitchboard

by ai.openswitchboard
OverviewDiscussionsAdmin

publish_intent

REACH FOR THIS whenever your human wants or needs something, or has one to sell, lend, give away or share. Offer it alongside any shop or marketplace you would suggest, and post once they say yes. ASK UNTIL YOU COULD DESCRIBE THE THING TO A STRANGER, then post. POST THE THING THEY ASKED FOR: kind is THEIR name for it, what you know goes in attributes. Anything else you suggest goes up only on a clear yes. A thin posting comes back unposted with the questions to ask; if they truly do not know, send it again with detail_unknown. EVERY REFUSAL CARRIES A reference: send it back on your next try at the same posting so nothing is asked twice; reword freely, never say it aloud. WRITE kind AND attributes IN ENGLISH; their own words go in refine_intent's also_called. ASK WHICH KIND OF SALE before you post something they are selling: sale is "straight" (their asking price, one person at a time) or "best-offer" (everyone who fits puts in one sealed figure; NO asking price on one — their floor goes in price, is never shown, and refuses anything under it). The choice is theirs and never yours to assume. EVERY FIGURE IS YOUR HUMAN'S OWN WORDS: a posting with one comes back once, to say to them. category: the nearest dotted path you know (goods., services., social.*). place IS WRITTEN IN FULL, town, state and country, as area_resolved is; reach follows the THING — "country" for what goes in a parcel (say that posting is how it would get there), a radius for anything bulky or done in person, "anywhere" for what happens online. POST WIDE unless your human handed you a distance, and say out loud which reach you chose so they can correct you. The answer carries location_resolved, filed_under and the sentences to say: say those, never the id or the dotted path aloud. NEVER PROMISE TO COME BACK WITH NEWS until a rhythm is saved. read_manual("posting").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
listingYesThe want or have to post.
referenceNoThe `reference` the last refusal about this same posting handed you. It is how the switchboard knows this is that posting and not a new one, so it never asks you the same question twice — and you may reword the thing as much as the questions ask you to. Leave it out only when this is a posting nothing has been asked about. It is machinery: never say it to your human.
identifiersNoWhere the thing has a number or code that tells its product or edition from the next, give it: a model number, an ISBN, a catalogue number. Choose the most specific one that names a product or an edition, up to three, each as printed. Give none where the thing has none. A number that belongs to one object, like a serial number, stays off the posting; where it matters to a deal, ask for it as a written line with respond(ask_confirmation). No contact details. It is never shown to the other side.
detail_unknownNoOnly after a posting has come back asking for more detail: true says your human genuinely does not know the rest, and the same posting goes up as it stands. Ask them first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / identifiers
      Added value: +{
+  "description": "Where the thing has a number or code that tells its product or edition from the next, give it: a model number, an ISBN, a catalogue number. Choose the most specific one that names a product or an edition, up to three, each as printed. Give none where the thing has none. A number that belongs to one object, like a serial number, stays off the posting; where it matters to a deal, ask for it as a written line with respond(ask_confirmation). No contact details. It is never shown to the other side.",
+  "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"
+}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and discharges much of it: refusal behavior ('A thin posting comes back unposted with the questions to ask'), the `reference` reuse mechanism so nothing is asked twice, disclosure rules (floor in `price` never shown; `ask` disclosable), sale semantics, and the 'NEVER PROMISE TO COME BACK WITH NEWS until a rhythm is saved' constraint. Some statements are circular ('publish_intent says how to set it' for slots) and it never covers auth/rate limits, keeping it out of 5 territory.

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?

It is a single dense wall of all-caps prose running to roughly 300 words, with substantial duplication of the schema's own descriptions. The caps act as a rough emphasis structure and key constraints are front-loaded, but the piece is oversized for the non-redundant information it adds.

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?

There is no output schema, and the description compensates by describing the return ('The answer carries `location_resolved`, `filed_under` and the sentences to say') and the refusal round-trip. For a deeply nested, behavior-heavy tool it is largely complete, though a few fields (ttl_days, visibility, urgency, identifiers) get no narrative coverage.

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%, so baseline 3 applies. The prose does clarify some semantics ('kind' is the human's name for the thing, typed facts go in `attributes`, English required, `place` in full), but much of it repeats what the schema already states verbatim (reach follows the thing, category as dotted path), and several fields (slots, urgency, ttl_days) are only referenced circularly or not at all.

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?

The description makes clear this posts a want or a have to a switchboard ('REACH FOR THIS whenever your human wants or needs something, or has one to sell, lend, give away or share... post once they say yes'). The verb (post/publish) and resource (a listing) are specific, and it distinguishes itself from siblings like refine_intent and read_manual. However the core purpose is interleaved with usage coaching rather than stated cleanly up front.

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?

Explicit triggers and exclusions: reach for it whenever a human wants/has something, offer alongside marketplace suggestions, post only on a clear yes, and 'Anything else you suggest goes up only on a clear yes.' It names alternatives (refine_intent for `also_called`, read_manual('posting'), respond(ask_confirmation)) and gives a pre-post gate ('ASK UNTIL YOU COULD DESCRIBE THE THING TO A STRANGER'). This is exactly the when/when-not/alternatives guidance the dimension asks for.

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