Skip to main content
Glama

workbench_investigate_crash

Collect bounded crash evidence for exact files by analyzing AST, Semgrep, linters, Git history, stack mapping, and static context while preserving each step's structured output and failure state.

Instructions

Bounded crash evidence collection for exact files: function AST/call candidates, Semgrep, language linter, Git blame/log, optional stack mapping, then two-engine static context. Does not claim an automatic root cause. Every step retains its structured output and failure state.

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>",
      "target_file_filter": "<target_file_filter>",
      "function_name": "<function_name>"
    },
    "name": "workbench_investigate_crash"
  }
}

Input Schema

NameRequiredDescriptionDefault
stackNo
binaryNo
case_idYes
load_biasNo
max_linesNo
symbolizerNollvm-symbolizer
timeout_msNo
address_kindNoruntime
function_nameYes
include_backendsNoExplicitly request supplementary REA/Craft source context. Source analysis normally uses native language tools first.
target_file_filterYesExact files relative to source_root. Directories and whole-repository globs are refused.
compile_commands_dirNo

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, openWorldHint=true, destructiveHint=false; the description adds genuinely new behavior by stating the work is 'bounded' and that 'every step retains its structured output and failure state' (partial-failure semantics). It does not disclose what, if anything, gets written to the case (relevant given readOnlyHint=false) or that case_id likely must come from workbench_create_case.

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?

Three sentences with no filler and the resource stated up front, but the middle sentence is a compressed comma-list of jargon that reads like a pipeline dump rather than structured information. Acceptably sized for the tool's complexity, not optimally organized.

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?

This is a complex, 12-parameter, open-world tool with no output schema and very low schema coverage, yet the description omits the case_id requirement/origin, the effect of a mutating call (readOnlyHint=false), and any hint of the returned evidence structure beyond 'retains its structured output'. It conveys scope but not enough for an agent to invoke it confidently.

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 only 17% across 12 parameters, so the description must compensate and largely fails to. It implicitly maps some inputs ('exact files' → target_file_filter, 'function AST' → function_name, 'optional stack mapping' → stack/binary/load_bias/symbolizer/address_kind), but case_id, compile_commands_dir, max_lines, and timeout_ms get no explanation anywhere.

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 names a specific verb+resource ('bounded crash evidence collection for exact files') and enumerates the concrete pipeline it runs (AST/call candidates, Semgrep, linter, Git blame/log, stack mapping, two-engine static context). It is clear what the tool produces and what it does not ('Does not claim an automatic root cause'), but it never positions itself against siblings like workbench_analyze, workbench_triage, or workbench_inspect_source.

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 implied rather than stated: 'for exact files' and the stack-mapping steps signal a crash-with-known-function investigation, and 'Does not claim an automatic root cause' sets expectations. There is no explicit when/when-not guidance and no named alternative for callers who don't have exact files or a stack.

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