Skip to main content
Glama

Call a vendor's API with your credentials

call_vendor
Destructive

Invokes a vendor API using the user's hidden credentials and returns the response; blocks data-changing requests unless writes are explicitly allowed. Large answers stay behind a handle for retrieval.

Instructions

Call a vendor's API with the user's credentials (never shown) and return its answer as sent. Writes are refused unless 'allow_writes' is true and the server allows them. A large answer stays behind the handle for 'fetch_raw'.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "call_vendor"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoFor a raw call: the JSON body.
hostNoFor a raw call: one of the vendor's other named hosts, if not its main one.
pathNoFor a raw call: a path on the vendor's API, starting with '/'.
queryNoFor a raw call: query parameters.
methodNoFor a raw call.
paramsNoThe endpoint's own inputs, named as vendor_endpoint lists them. An undeclared one is refused.
vendorNoFor a raw call: the vendor's slug.
endpointNoA catalog endpoint id, its inputs in 'params'; or give 'vendor', 'method' and 'path'.
allow_writesNoRequired to change data. Ask the user first, and dry-run (validateOnly etc.) before.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already flag destructive=true, openWorld=true, and non-idempotent, so the safety profile is known. The description adds real value by explaining that writes are gated behind 'allow_writes' and server policy, that credentials are never exposed, and that oversized answers are parked behind a handle — but it does not say what a refused write returns or how the handle is obtained.

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?

Three short sentences with zero filler, front-loading the core action before the write restriction and the large-response caveat.

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 nine optional parameters, nested objects, and no output schema, the description covers the two axes an agent most needs: write gating and handling of large answers. The raw-call versus catalog-endpoint mode split is only implicit here, which is the main remaining gap.

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 coverage is 100% and every parameter already carries its own description, so the baseline applies. The description reinforces the meaning of 'allow_writes' as a write gate and hints at the response handle, but adds no syntax or format detail beyond the schema.

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 specific verb and resource: call a vendor's API using the user's credentials and return the answer verbatim. It is clearly distinct from retrieval-style siblings, though it does not explicitly name vendor_endpoint as the catalog-based alternative, leaving that distinction to the 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?

It gives a clear when-not rule ('Writes are refused unless allow_writes is true') and routes large responses to the fetch_raw sibling. It does not spell out when to prefer the catalog endpoint path over a raw call, which the schema handles instead.

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