Skip to main content
Glama

use_tool

Call any PazAIr tool by name, also one that is not in the list you were given (find_tools names them). The same rules as a direct call: a tool that needs a key needs it here too, and the answer is the tool's own.

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": {
      "name": "<name>"
    },
    "name": "use_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe name of the tool, e.g. dispute_order.
api_keyNoyour key, if your client cannot send headers
argumentsNoThe arguments of that tool, as its definition from find_tools says. Leave out for a tool without arguments.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / api_key
      Added value: +{
      +  "description": "your key, if your client cannot send headers",
      +  "type": "string"
      +}
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent, closed-world), so the description's job is narrower. It adds real beyond-annotation behavior: credential pass-through ("a tool that needs a key needs it here too") and response passthrough ("the answer is the tool's own"). It does not cover failure behavior for an unknown tool name or whether the wrapper alters errors.

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?

Two short sentences with the core capability front-loaded and no filler. The phrasing "also one that is not in the list you were given" is slightly convoluted but compact and load-bearing.

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 generic dispatcher with nested arguments and no output schema, the essentials are present: how to name the tool, that credentials may be needed, and that the response is the target tool's own. Missing is any statement about what happens when the name is invalid or the tool errors, which matters more here than for a normal single-purpose tool.

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 three parameters, including the nested arguments object, are already documented. The description adds only one nuance beyond the schema, that the name may refer to a tool absent from the provided list; otherwise the schema does the work, which is the baseline-3 case.

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?

"Call any PazAIr tool by name" gives a specific verb and resource, and the parenthetical that the name may be one "not in the list you were given" explains the dispatcher role that separates it from every sibling. It is clear, though it never explicitly says this is a generic indirection layer versus the named sibling tools.

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 only implied: the aside about tools not in the given list plus "find_tools names them" hints at the discovery-then-dispatch flow, and "The same rules as a direct call" implies a direct call is the alternative. There is no explicit when-to-use-this-instead-of-calling-directly statement or exclusion.

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