Skip to main content
Glama

workbench_triage

Read project manifests and sample languages to discover test, lint, and typecheck commands and installed adapters without running code, then return source plans or use real backends for artifacts.

Instructions

Read project manifests and sample languages; discover named test/lint/typecheck commands and installed adapters without executing project code. Source projects receive a plan; compiled/ASAR artifacts or explicit target_type=javascript/native/artifact use the appropriate real backends. Missing capability is explicit.

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>"
    },
    "name": "workbench_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
case_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and the description usefully adds that no project code is executed and that missing capability is surfaced explicitly rather than silently. However, with readOnlyHint=false it never explains what state is actually written (presumably the case record/plan), leaving a real ambiguity for a mutating tool. The added context is valuable but does not fully cover the behavior profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core verb is front-loaded in the first clause, which is good, but the first sentence is a semicolon-packed run-on and closing fragments like 'Missing capability is explicit' are too compressed to parse without effort. No filler sentences, but readability suffers from density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool whose only input is an unexplained UUID and which has no output schema, the description should say what a triage call produces (a plan? a capability report?) and what happens on the artifact vs source branches. It gestures at these but never specifies the return shape or what the case_id binds to, leaving meaningful gaps for a first invocation.

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% and the sole parameter, case_id, is never explained — the agent must guess where the case identifier comes from or whether one must be created first via workbench_create_case. Worse, the description references an 'explicit target_type=javascript/native/artifact' control that does not exist anywhere in the input schema, which can send an agent looking for a parameter it cannot supply.

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 gives concrete verbs and resources: read project manifests, sample languages, discover test/lint/typecheck commands and installed adapters. That is a specific 'triage/survey a project' purpose an agent can distinguish from heavier siblings like workbench_analyze or workbench_run_check. It stops short of naming any sibling explicitly, so it is clear but not differentiated.

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 through branch conditions: source projects get a plan, while compiled/ASAR artifacts or an explicit target_type go to 'real backends.' There is no statement of when to call this versus workbench_analyze, workbench_inspect_source, or workbench_discover_tools, and no preconditions. The agent must infer that triage precedes deeper analysis.

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