Skip to main content
Glama

vet_seller

Read-onlyIdempotent

Whether a shopper can safely buy from a seller: a verdict with its key reasons, for any online store or Amazon / Walmart seller, in 1-20 seconds. Pass a seller id (from find_deals), account key, seller or store URL, domain, product link or store name. status: found; ambiguous (several matches, listed in message: call again with one of them, or with a domain or seller link); not_found (no verdict, neither a good nor a bad sign; message says why). When found, relay summary as it is (it includes buyer_notes); seller_name is who was rated (may differ from the input). trust_level, best to worst: trusted, reliable, limited (little vouches for it; not a warning), caution (a concrete sign to weigh), risky (strong signs of a scam or impostor); unknown means not enough information. reasons: what the verdict rests on; buyer_notes: what to know whatever the verdict; facts: the evidence, null meaning not known. Risk is read from visible evidence, not a finding of counterfeits.

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": {
      "seller": "<seller>"
    },
    "name": "vet_seller"
  }
}

Input Schema

NameRequiredDescriptionDefault
sellerYesThe seller: a seller id from find_deals, an account key (amazon.com:<id>), a seller page or store URL, a store domain, a product page link or a store name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / seller / description
      Previous value: -"The seller: a seller id from get_offer or find_deals, an account key (amazon.com:<id>), a seller page or store URL, a store domain, a product page link or a store name."New value: +"The seller: a seller id from find_deals, an account key (amazon.com:<id>), a seller page or store URL, a store domain, a product page link or a store name."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the bar is lower, yet the description adds a lot: 1-20 second latency, a full enumeration of status values, the ordered trust_level scale with meanings, and the caveat that risk is read from visible evidence and is not a counterfeit finding. It also flags that seller_name may differ from the input.

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?

Front-loads the verdict and timing, then covers input forms, status handling, and the meaning of each returned field in a tight sequence. Dense parenthetical style but essentially no wasted sentence.

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?

With one parameter and no output schema, the description carries the full burden and does explain every returned field (summary, seller_name, trust_level, reasons, buyer_notes, facts). Minor gap: it doesn't say what a not_found or ambiguous response leaves in the other fields, but overall it is sufficient to call and interpret the tool.

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 100% and the schema already lists accepted input forms, so the baseline is 3; the description still adds meaning by tying the most reliable form to find_deals ids and by explaining which fallback inputs (domain or seller link) resolve an ambiguous result. It does not add format or length constraints beyond the schema.

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?

States a specific verb and resource ('whether a shopper can safely buy from a seller: a verdict with its key reasons') and scopes it to any store or Amazon/Walmart seller, which distinguishes it from vet_price and the deal-search siblings. An agent can tell what it returns (a verdict plus reasons) without opening any schema.

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 routing guidance: pass a seller id from find_deals, and on 'ambiguous' call again with one of the listed matches or with a domain/seller link. It also tells the agent to relay summary verbatim and to treat not_found as neither good nor bad. It does not explicitly contrast with vet_price, so not a 5.

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