Skip to main content
Glama

workbench_call

Calls an advertised upstream tool with arguments, stores the original response and provenance, and returns a compact preview plus a record ID; failures are retained and surfaced as errors.

Instructions

Call an exact advertised upstream tool. Stores the original response with arguments, runtime/session identity and hash. Returns a compact preview and record ID. Failures are retained and surfaced as errors.

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": {
      "case_id": "<case_id>",
      "backend": "<backend>",
      "tool": "<tool>"
    },
    "name": "workbench_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolYes
backendYes
case_idYes
argumentsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior4/5

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

Annotations already declare a non-read, open-world, non-destructive call, and the description adds genuinely useful context beyond them: the call stores the original response with arguments, runtime/session identity and a hash, returns a compact preview plus a record ID, and retains failures as errors. This explains the write side effect and error semantics that the annotations only gesture at.

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?

Four tight sentences, front-loaded with the core action and then the persistence, return, and failure characteristics. No filler, though the wording is dense enough that a skimming agent could miss the storage side effect.

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?

Return shape is described (preview + record ID) and no output schema exists, so that is covered, and failure behavior is stated. However, for an open-world dispatcher with nested free-form arguments and zero schema coverage, the definition omits the discovery prerequisite and the meaning of three required parameters, leaving real gaps.

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 0% across four parameters (case_id, backend, tool, arguments), so the description carries the full burden and largely fails. It hints that 'tool' names an advertised tool and that 'arguments' are the upstream arguments, but leaves case_id, the rea/craft backend enum, and the requirement that arguments match the target tool's schema unexplained.

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?

States a specific verb and role: 'Call an exact advertised upstream tool,' making it clear this is the generic dispatcher to a discovered tool. It is distinguishable from siblings like workbench_run_check or workbench_analyze, though the jargon 'advertised upstream' is left for the agent to decode.

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

Usage Guidelines2/5

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

No explicit when-to-use or when-not-to-use guidance, and no mention of alternatives or prerequisites. The word 'advertised' weakly implies the tool must first be surfaced via workbench_discover_tools, but that dependency is never stated.

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