Skip to main content
Glama

find_and_buy

Décrire un besoin en langage naturel (« jours fériés en France », « derniers dépôts SEC de Tesla », « réserver une table pour 4 »…) : Vantro choisit le meilleur outil selon la pertinence, la fiabilité mesurée et le prix, l'exécute et bascule sur un autre en cas d'échec.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "need": "<need>"
    },
    "name": "find_and_buy"
  }
}

Input Schema

NameRequiredDescriptionDefault
needYes
paramsNoParamètres à transmettre à l'outil choisi (ex. query, place, ticker…)
categoryNo
max_price_eurNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3/5.0
Behavior2/5

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

No annotations exist, so the description carries the full behavioral burden. It does disclose genuine traits — automatic tool selection, price/reliability ranking, and failover on failure — which is more than most. But for a tool whose name implies spending money it never says whether a purchase is committed, whether payment is debited, whether max_price_eur is a hard cap, whether actions are reversible, or what is returned. Those omissions are serious for an unannotated executing tool.

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?

A single dense sentence that front-loads the core mechanic and uses parenthetical examples efficiently; nothing is redundant. It is slightly overloaded by three long examples, but each example earns its place by broadening the perceived scope.

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 4-parameter, nested-object meta-tool with no annotations and no output schema, the definition covers the selection/execution/failover mechanic adequately. It falls short on the two things an agent most needs: what the call returns (selected tool? raw result? order reference?) and the payment/commitment semantics implied by find_and_buy.

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

Parameters2/5

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

Schema description coverage is only 25% (just the nested params object), so the description must compensate. It maps loosely onto need (the natural-language request) and touches price via 'le prix', but never defines max_price_eur as a ceiling in EUR, never explains what category filters on, and never clarifies how the nested params object is matched to the dynamically chosen tool. Meaning added beyond the schema is thin.

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 states a concrete pipeline: the agent supplies a natural-language need, Vantro selects the best tool by relevance, measured reliability and price, executes it, and falls back on failure. That distinguishes it reasonably well from single-purpose siblings like search_tools, quote or buy. The gap is that nothing in the text explains the 'buy' half of the name — payment/charging is never mentioned, only price as a selection criterion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is conveyed by three worked examples ('jours fériés en France', 'derniers dépôts SEC de Tesla', 'réserver une table pour 4') that imply 'use this when you have a goal rather than a known tool'. However, no alternative is named: it never says to call search_tools/get_tool explicitly when you already know the tool, or whether buy/quote should be preferred for known purchases. Guidance is implied rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources