Skip to main content
Glama

Surfing Dog Inbox

by ai.surfingdog
OverviewDiscussionsAdmin

Place an order

create_order
Idempotent

Order products. Prices are in minor units. A line naming a product (productId or sku) costs the business's price from list_products, and the total follows; a different price you send is only noted for the business. A line naming no product waits for the business to price it. A priced order binds your person only once they confirmed it: without terms_sha nothing is sent, and you get the summary to show them (confirm.summary, confirm.terms_sha); call again with that terms_sha on their clear yes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoThe person's key (sdkey1_…), if that is all you have: it is exchanged once for a pass, which comes back in identity.passes — keep the pass and send it next time instead. Never stored.
passNoThe person's passes (sdpass1_…), space-separated, at most 8: presented to the network that issued each, so the business recognises the customer. Or send them in the Sdi-Pass header. Never stored.
contactNo
messageNo
payloadYes
terms_shaNoThe fingerprint of the terms your person confirmed (details.terms_sha of the 409 confirm_terms a priced request without it gets). Nothing is sent to the business without it when the request carries a price.
idempotency_keyNoSame key + same request = same answer. Required for agents.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / payload / properties / orderedItem / items / properties / listPrice
      Added value: +{
+  "properties": {
+    "currency": {
+      "maxLength": 3,
+      "minLength": 3,
+      "type": "string"
+    },
+    "value": {
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "value",
+    "currency"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / payload / properties / personalised
      Added value: +{
+  "properties": {
+    "listPrice": {
+      "properties": {
+        "currency": {
+          "maxLength": 3,
+          "minLength": 3,
+          "type": "string"
+        },
+        "value": {
+          "maximum": 9007199254740991,
+          "minimum": 0,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "value",
+        "currency"
+      ],
+      "type": "object"
+    },
+    "says": {
+      "maxLength": 200,
+      "type": "string"
+    }
+  },
+  "required": [
+    "listPrice"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / terms_sha
      Added value: +{
+  "description": "The fingerprint of the terms your person confirmed (details.terms_sha of the 409 confirm_terms a priced request without it gets). Nothing is sent to the business without it when the request carries a price.",
+  "pattern": "^[A-Za-z0-9_-]{43}$",
+  "type": "string"
+}
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Goes beyond the annotations (readOnlyHint=false, idempotentHint=true) by disclosing the crucial safety behaviour: nothing is sent to the business without terms_sha when a price is present, a sent price differing from the list price is only noted, and a priced order only binds the person after explicit confirmation. This is exactly the write-semantics an agent needs and cannot get from structured fields.

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?

Front-loaded with the core action and the pricing rule in the first two short sentences. Later sentences get dense and slightly convoluted, but every clause carries real semantic content about the confirm flow, so there is little waste.

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 7-parameter nested write tool with no output schema, the description covers pricing, line types, and the two-phase confirmation, and even names the returned confirm.summary/confirm.terms_sha. Authentication via key vs pass is left to the schema, which documents it well, so coverage is nearly 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 only 57%, and the description compensates by clarifying that prices are in minor units and by explaining how orderedItem lines relate to productId/sku and to the total, none of which the schema documents. It stops short of covering the remaining opaque fields deliberately (contact, delivery, paymentMethod).

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+resource ("Order products") and delineates scope via pricing behaviour, which separates it from quote/offer siblings like request_quote and make_offer. It is clear what the tool does, though the two-phase confirm behaviour makes it slightly less crisp than a single-purpose definition.

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?

Gives concrete context: name a product to take the business's list price, omit one to leave it for the business to price, and call again with terms_sha on a clear yes. It implies when to send a price vs wait, but never names an alternative sibling (e.g. request_quote) or states an explicit when-not condition.

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

All Surfing Dog Inbox 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