Skip to main content
Glama

crash_load

Loads an ELF core or Windows minidump into the session to detect format, architecture, threads, modules, and exception details before crash analysis, without executing the dump.

Instructions

Load a crash dump (ELF core or Windows minidump) into the session.

Use first, before any other crash_* tool. Detects format, architecture, threads, modules and exception info. Does not execute the dump. Missing binaries/symbols are reported, not guessed.

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": {
      "dump_path": "<dump_path>"
    },
    "name": "crash_load"
  }
}

Input Schema

NameRequiredDescriptionDefault
dump_pathYes
binary_pathsNo
symbols_pathNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that the dump is parsed but not executed, that it extracts format, architecture, threads, modules and exception info, and that missing binaries/symbols are reported rather than guessed. Remaining gaps are side effects on existing session state (does loading replace a prior dump?) and any size or permission limits.

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

Conciseness5/5

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

Four short sentences, front-loaded with the action and the ordering constraint, then format coverage, then behavior. Each sentence contributes a distinct fact (what, when, what it extracts, what it refuses to do) and there is no repetition of the tool name or filler.

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

Completeness4/5

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

An output schema exists, so return-value explanation is rightly omitted, and the description covers ordering, formats, extracted metadata, and error philosophy. For a 3-parameter loader it is nearly complete; only parameter path conventions and session-state effects are missing.

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 3 parameters (dump_path, binary_paths, symbols_path), so the description must compensate and largely does not. It never names or explains the parameters; "Missing binaries/symbols are reported" only indirectly hints at the binary_paths and symbols_path roles, and nothing clarifies accepted path formats, relative vs absolute, or how binary_paths should be ordered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Load a crash dump") and names the accepted formats (ELF core, Windows minidump), which no sibling name implies. The second paragraph positions it relative to the other crash_* tools, so an agent can distinguish it from crash_disassemble or crash_summary without reading schemas.

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

Usage Guidelines4/5

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

Explicit sequencing guidance: "Use first, before any other crash_* tool" tells the agent the prerequisite ordering, which is the main usage decision for this tool. It stops short of stating failure modes (e.g., what to do if the dump is already loaded or the format is unsupported), so it falls just below the top score.

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