Skip to main content
Glama
Sign In

BetSlip Doctor

by ai.betslipdoctor
OverviewDiscussionsAdmin

History: record a bet, notes, links

history_actions
Idempotent

Write this account's History as the app does. Record a bet only when the customer says they placed it. report_advice_response: POST history/advice/response {reportId, reportDigest, expectedRevision, confirmation: SAVE_RESPONSE, input: {exposure, decision, claimedViewedAt, claimedDecisionAt, modifiedTicketId}}; read report_advice first, show the exact response to the customer and send only after their explicit confirmation; reuse commandKey on retry; save_manual: POST history/manual {id?, expectedRevision?, confirmation PLACED, input {ticketId, placedAt, status, outcome, ...}}; set_currency: POST history/currency app body; save_link: POST history/links app body (link an import to a manual record); recall_save: POST history/recall/organization app body (notes, tags, bookmark). Confirm the requested change with the customer before a write. A valid write is sent without a separate MCP preview unless the action says otherwise.

Input Schema

NameRequiredDescriptionDefault
bodyNoThe app request body for this action, unchanged.
actionYes
commandKeyNoWrites: one stable key per write, reused on every retry.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / allOf
      Added value: +[
+  {
+    "if": {
+      "properties": {
+        "action": {
+          "const": "report_advice_response"
+        }
+      },
+      "required": [
+        "action"
+      ]
+    },
+    "then": {
+      "properties": {
+        "body": {
+          "$schema": "https://json-schema.org/draft/2020-12/schema",
+          "additionalProperties": false,
+          "properties": {
+            "confirmation": {
+              "const": "SAVE_RESPONSE",
+              "type": "string"
+            },
+            "expectedRevision": {
+              "maximum": 999999999,
+              "minimum": 0,
+              "type": "integer"
+            },
+            "input": {
+              "additionalProperties": false,
+              "properties": {
+                "claimedDecisionAt": {
+                  "anyOf": [
+                    {
+                      "format": "date-time",
+                      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "claimedViewedAt": {
+                  "anyOf": [
+                    {
+                      "format": "date-time",
+                      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "decision": {
+                  "enum": [
+                    "unknown",
+                    "followed",
+                    "modified",
+                    "rejected"
+                  ],
+                  "type": "string"
+                },
+                "exposure": {
+                  "enum": [
+                    "unknown",
+                    "unseen",
+                    "viewed"
+                  ],
+                  "type": "string"
+                },
+                "modifiedTicketId": {
+                  "anyOf": [
+                    {
+                      "format": "uuid",
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              },
+              "required": [
+                "exposure",
+                "decision",
+                "claimedViewedAt",
+                "claimedDecisionAt",
+                "modifiedTicketId"
+              ],
+              "type": "object"
+            },
+            "reportDigest": {
+              "pattern": "^[a-f0-9]{64}$",
+              "type": "string"
+            },
+            "reportId": {
+              "format": "uuid",
+              "type": "string"
+            }
+          },
+          "required": [
+            "reportId",
+            "reportDigest",
+            "expectedRevision",
+            "confirmation",
+            "input"
+          ],
+          "type": "object"
+        }
+      },
+      "required": [
+        "commandKey",
+        "body"
+      ]
+    }
+  }
+]
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "save_manual",
-  "set_currency",
-  "save_link",
-  "recall_save"
-]New value: +[
+  "report_advice_response",
+  "save_manual",
+  "set_currency",
+  "save_link",
+  "recall_save"
+]
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the annotations (idempotentHint=true, destructiveHint=false), the description discloses genuinely useful behavior: commandKey must be reused on retries, a valid write is sent without a separate MCP preview, and a specific confirmation handshake is required before report_advice_response. That last point is a real workflow constraint the agent could not derive from the schema or annotations, though return values and failure behavior are not discussed.

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?

Purpose and the core safety rule are front-loaded, and the per-action block is labelled rather than free-form prose, so it is skimmable despite being telegraphic. The semicolon-chained API notation ("POST history/currency app body") is dense, but almost no sentence is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-action write tool with no output schema, the description covers the two most consequential actions in detail (report_advice_response, save_manual) but reduces set_currency, save_link, and recall_save to "POST ... app body" with a parenthetical gloss, leaving three of five operations effectively unspecified. Nothing is said about what a successful write returns or how conflicts on expectedRevision surface.

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?

The description maps each action enum value to its expected body shape, which is the most useful thing it can add for a multiplexed action parameter and is easier to read than the allOf conditional. However, it largely restates field names already present in the schema, and the meanings of semantically loaded fields (exposure, decision, claimedViewedAt, modifiedTicketId) are never explained, leaving the 67% schema coverage gap unfilled.

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 opens with a specific verb+resource ("Write this account's History as the app does") and then enumerates the five supported operations with their HTTP targets, so the agent knows exactly what class of mutation this is. It does not name a sibling to contrast against (e.g. ticket_actions, export_betting_history, show_history_records), so differentiation is left implicit via the "write" framing.

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 preconditions per action: record a bet only when the customer states they placed it, run read report_advice first, show the exact response, and send only after explicit confirmation; also the general rule to confirm any requested change with the customer before a write. It stops short of naming which sibling to use instead when the job is a read (get_history_summary, show_history_records) or a ticket edit (ticket_actions).

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

All BetSlip Doctor 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