upgrade-agent

Predict Bid Success

predict_bid_success

Read-onlyIdempotent

Estimates how likely a specific bid amount is to be accepted, grounded in Plusgrade's resolved bid outcomes for the carrier and cabin, plus the operator's own bid-strength read when a checked booking's session id is provided. Returns null when there isn't enough data.

Input Schema

TableJSON Schema

Name	Required	Description
`cabin`	No	Optional: target cabin.
`amount`	Yes	The bid amount to evaluate, in the operator's offer currency.
`carrier`	No	Operator IATA code or name, e.g. 'LH' or 'Lufthansa'. Optional if conversationId carries the operator from earlier.
`segment`	No	Route 'YUL-LHR' or flight number, if the booking has more than one bid-eligible segment.
`sessionId`	No	The sessionId from start_eligibility_check — unlocks the operator's LIVE bid-strength read for this exact booking and amount.
`conversationId`	No	Optional stable conversation id — reuses the operator (and checked booking) in play.
`travelerQuestion`	No	The traveler's request in their own words, verbatim (e.g. 'can I upgrade my Swiss flight to business?'). For privacy, leave out the booking reference, last name, email, and other personal details. Pass it whenever the traveler asked in free text — it improves Upgrade Agent's answers over time.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 22, 2026

changedOutput schema / (root)

Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "band": {
-      "type": [
-        "string",
-        "null"
-      ]
-    },
-    "bidAnalysis": {
-      "anyOf": [
-        {
-          "additionalProperties": false,
-          "properties": {
-            "score": {
-              "type": [
-                "number",
-                "null"
-              ]
-            },
-            "strength": {
-              "type": "string"
-            },
-            "text": {
-              "type": [
-                "string",
-                "null"
-              ]
-            }
-          },
-          "required": [
-            "strength"
-          ],
-          "type": "object"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "The operator's own LIVE strength read for this amount on this booking (present when sessionId resolves to a checked booking)."
-    },
-    "confidence": {
-      "type": [
-        "string",
-        "null"
-      ]
-    },
-    "note": {
-      "description": "Why no probability was returned (invalid input / unknown operator / insufficient resolved outcomes). Relay this honestly.",
-      "type": "string"
-    },
-    "probability": {
-      "description": "Estimated success probability (0–1), or null when there's too little resolved data.",
-      "type": [
-        "number",
-        "null"
-      ]
-    },
-    "samples": {
-      "description": "Number of resolved bids the estimate is based on.",
-      "type": [
-        "number",
-        "null"
-      ]
-    }
-  },
-  "type": "object"
-}New value: +null

Changed5 schema fields changedSep 22, 2026

changedInput schema / properties / conversationId / description

Previous value: -"Optional stable conversation id — reuses the operator in play."New value: +"Optional stable conversation id — reuses the operator (and checked booking) in play."

addedInput schema / properties / segment

Added value: +{
+  "description": "Route 'YUL-LHR' or flight number, if the booking has more than one bid-eligible segment.",
+  "type": "string"
+}

addedInput schema / properties / sessionId

Added value: +{
+  "description": "The sessionId from start_eligibility_check — unlocks the operator's LIVE bid-strength read for this exact booking and amount.",
+  "type": "string"
+}

changedInput schema / properties / travelerQuestion / description

Previous value: -"The traveler's request in their own words, verbatim (e.g. 'can I upgrade my Swiss flight to business?'). NEVER include the booking reference, last name, email, or other personal details. Pass it whenever the traveler asked in free text — it improves Upgrade Agent's answers over time."New value: +"The traveler's request in their own words, verbatim (e.g. 'can I upgrade my Swiss flight to business?'). For privacy, leave out the booking reference, last name, email, and other personal details. Pass it whenever the traveler asked in free text — it improves Upgrade Agent's answers over time."

addedOutput schema / properties / bidAnalysis

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "score": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "strength": {
+          "type": "string"
+        },
+        "text": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "strength"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The operator's own LIVE strength read for this amount on this booking (present when sessionId resolves to a checked booking)."
+}

Changed1 schema field changedJul 8, 2026

addedInput schema / properties / travelerQuestion

Added value: +{
+  "description": "The traveler's request in their own words, verbatim (e.g. 'can I upgrade my Swiss flight to business?'). NEVER include the booking reference, last name, email, or other personal details. Pass it whenever the traveler asked in free text — it improves Upgrade Agent's answers over time.",
+  "type": "string"
+}

Changed1 schema field changedJul 8, 2026

addedOutput schema / properties / note

Added value: +{
+  "description": "Why no probability was returned (invalid input / unknown operator / insufficient resolved outcomes). Relay this honestly.",
+  "type": "string"
+}

AddedJul 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is safe and non-mutating. The description adds context by explaining the data sources (historical outcomes, optional live read) and the null return when data is insufficient. It doesn't contradict annotations and provides value beyond them, but it doesn't detail all behavioral edge cases (e.g., error conditions beyond null).

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?

The description is two sentences, front-loaded with the core purpose. The first sentence states the main function and data grounding; the second notes the null return. There is no redundant wording or unnecessary detail. It is compact and immediately scannable.

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?

With 7 parameters and no output schema, the description should clarify the return format. It says 'how likely' and 'returns null when there isn't enough data,' implying a numeric value but not specifying the scale (e.g., 0-1 probability, percentage, or score). It also doesn't state what 'enough data' means or any prerequisites for using sessionId. Given the complexity, this is a notable gap, though the description does cover the core behavior.

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 all seven parameters already have detailed descriptions in the schema. The tool description does not add significant parameter-specific meaning beyond what the schema provides. It mentions the sessionId's role ('unlocks the operator's LIVE bid-strength read') which aligns with the schema description, but the schema already covers this. Baseline 3 is appropriate since the schema carries the semantic load.

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 clearly states a specific verb and resource: 'estimates how likely a specific bid amount is to be accepted.' It also specifies the data sources (Plusgrade's resolved bid outcomes, operator's bid-strength read) and distinguishes itself from siblings like place_bid, get_bid_status, and modify_bid by focusing on prediction rather than execution or status. The purpose is unambiguous.

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?

The description implies when to use it: before placing a bid, to evaluate the likelihood of acceptance. It notes that a sessionId unlocks a live read, and it returns null when data is insufficient. However, it does not explicitly compare against alternatives like 'use this instead of place_bid when you want to assess success likelihood' or state when not to use it. It's clear but lacks explicit exclusion guidance.

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

All upgrade-agent tools Inspect

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

Need Help?