upgrade-agent

Predict Bid Success

predict_bid_success

Read-onlyIdempotent

Given a SPECIFIC bid amount, returns the probability it succeeds, grounded in Plusgrade's own resolved accept/reject outcomes for this carrier and cabin — never a guess. Use this when a traveler asks something like 'will $400 get me the upgrade?' or before confirming a bid amount with place_bid. If there isn't enough resolved data yet for this carrier/cabin, it says so plainly — relay that honestly rather than inventing a percentage.

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.
`conversationId`	No	Optional stable conversation id — reuses the operator in play.
`travelerQuestion`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description
`band`	No
`note`	No	Why no probability was returned (invalid input / unknown operator / insufficient resolved outcomes). Relay this honestly.
`samples`	No	Number of resolved bids the estimate is based on.
`confidence`	No
`probability`	No	Estimated success probability (0–1), or null when there's too little resolved data.

TDQS

A4.8/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint false), the description adds that results are grounded in real outcomes, never guesses, and that it will honestly report insufficient data. No contradiction with annotations.

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 concise with two core sentences followed by practical notes. Every sentence adds value, and the key information is front-loaded.

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

Completeness5/5

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

Given the tool's complexity (5 params, 1 required, output schema exists), the description covers purpose, usage, data provenance, and edge cases (insufficient data). It is fully self-contained and informative.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description reinforces the key parameter (amount) and adds critical usage guidance for travelerQuestion (e.g., do not include personal details), providing extra utility.

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 the tool predicts probability of bid success given a specific bid amount, grounded in historical data. It distinguishes itself from siblings by emphasizing data-driven accuracy and providing concrete use cases.

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?

Explicitly states when to use (traveler asks about a bid amount, before confirming with place_bid) and how to handle insufficient data. While it doesn't list when not to use, the guidance is clear and actionable.

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

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation5/5

Each tool targets a distinct function or workflow step (e.g., general info vs booking-specific check, bid placement vs bid status, partner lookup vs pricing), and descriptions clarify when to use which. Even overlapping actions like check_upgrade_eligibility and start_eligibility_check are clearly differentiated by context.

Naming Consistency4/5

Most tools follow a verb_noun pattern (e.g., check_upgrade_eligibility, place_bid, get_bid_status). A few deviate slightly (partner_question_insights, usage_totals) but the naming is still intuitive and readable overall.

Tool Count4/5

17 tools is at the upper end of typical but still well-scoped given the breadth of functionalities (eligibility, bidding, watch, partner info, analytics). Every tool has a clear purpose, so the count feels justified rather than bloated.

Completeness4/5

The tool set covers the full lifecycle of upgrade management: eligibility check, bid placement/modification/status, pricing, partner info, watch, and system metrics. A minor gap is the absence of a cancel bid tool, but the main workflows are complete.

Resources

Need Help?