Skip to main content
Glama

workbench_create_case

Start a shared reverse-engineering, bug-diagnosis, or optimization investigation; define target and goal, set source_root for source inspection, and authorize only named test commands when permitted.

Instructions

Start a shared reverse-engineering, bug-diagnosis or optimization investigation. Set source_root for source inspection. allow_execution authorizes named project test commands only; use it only with user authorization.

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": {
      "mode": "<mode>",
      "target": "<target>",
      "goal": "<goal>"
    },
    "name": "workbench_create_case"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYes
modeYes
actualNo
targetYes
expectedNo
source_rootNo
target_typeNoauto
allow_executionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds genuinely non-redundant behavior: this creates a shared investigation object, source_root enables source inspection, and allow_execution is narrowly scoped to named test commands and gated on explicit user authorization. That authorization caveat is the kind of safety context annotations cannot express. It stops short of 5 because nothing is said about what the call yields or the case lifecycle.

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?

Three tight sentences with the purpose front-loaded and parameter notes following. No filler and no restatement of the tool name. Slightly clipped phrasings ('Set source_root for source inspection') could be marginally more explicit, but the structure is efficient.

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 an 8-parameter, state-creating tool with no output schema, the description covers purpose, two key parameters, and the authorization constraint. It does not explain the actual/expected fields, what identifier or handle comes back for use with workbench_close_case and workbench_record_finding, or what 'shared' implies about visibility to other parties. Adequate but with visible gaps.

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 0% across 8 parameters, so the description must carry the load. It explains source_root and allow_execution -- arguably the two highest-risk parameters -- but leaves target, goal, actual, and expected completely unelaborated. The two enums (mode, target_type) are largely self-describing, which limits the damage, but the semantic gap on the debug-pair fields (actual/expected) is real.

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 opens with a specific verb and resource: 'Start a shared reverse-engineering, bug-diagnosis or optimization investigation,' which maps cleanly onto the mode enum values (reverse/debug/optimize). An agent can tell this is the case-creation entry point. It does not name or contrast any sibling (e.g., workbench_analyze or workbench_investigate_crash), so it stays short of a 5.

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?

There is conditional guidance for two parameters: source_root is for source inspection, and allow_execution is only for named project test commands and only with user authorization. However, there is no statement of when to pick this tool versus the many siblings, nor any prerequisite about what a case is needed for. Usage is implied rather than routed.

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