Skip to main content
Glama

Inspect Recorded Crash

inspect_recorded_crash
Idempotent

Inspect a Linux ELF64 core dump without launching the target or attaching to a live PID; return segments, notes, PRSTATUS registers, SIGINFO, SHA-256 evidence, optional GDB/pwndbg mapping candidates.

Instructions

Inspect a supplied Linux ELF64 amd64 little-endian core without launching its target or attaching to any live PID. Returns all recorded segments, raw note owners/descriptors and source ranges, every Linux CORE PRSTATUS thread/register and SIGINFO fields inline with SHA-256 Evidence. Historical PID is recorded metadata; current process/file identity, note coverage and signal-thread associations stay unknown. Optionally add derived core-only GDB/pwndbg mapping candidates through explicit BYO configuration; zero map flags mean unknown permissions. Uses the same stable snapshot for both stages, bounded complete output and owned cleanup. Initial Linux x64 profile: unchanged pwntools 4.15.0/pyelftools 0.33/Unicorn 2.1.2; optional unchanged pwndbg 2026.09.15. No implicit executable/library pairing, GDB command language, host configuration changes or dependency installation.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "/artifacts/crash.core"
    },
    "name": "inspect_recorded_crash"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute filesystem path to a supplied Linux ELF core
include_debugger_contextNoAdd core-only mapping candidates through caller-supplied GDB/pwndbg

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=true and destructiveHint=false; the description adds substantial behavior beyond that. It discloses that both stages share the same stable snapshot, that output is bounded and cleanup is owned (consistent with readOnlyHint=false), that no host configuration changes or dependency installation occur, and that it pins exact dependency versions. Most valuably, it states what stays unknown — current process/file identity, note coverage, and signal-thread associations — which prevents the agent from over-claiming results.

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 purpose and exclusions are front-loaded, which is good, but the body is a series of long multi-clause sentences that are hard to parse on one read ('raw note owners/descriptors and source ranges, every Linux CORE PRSTATUS thread/register and SIGINFO fields inline with SHA-256 Evidence'). The pinned dependency versions (pwntools 4.15.0 / pyelftools 0.33 / Unicorn 2.1.2 / pwndbg 2026.09.15) add little for tool selection and inflate length, while phrases like 'bounded complete output and owned cleanup' are too compressed to be actionable.

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?

There is no output schema, so the description carries the return-value burden and does it well: it enumerates segments, notes, PRSTATUS threads/registers, SIGINFO fields, and evidence hashing. Combined with the explicit unknown-field disclosure, an agent knows what it will and will not receive. Gaps remain around failure modes (non-ELF64, wrong architecture, truncated or missing file) and any size/limit behavior of the bounded output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description nevertheless adds real meaning: the core must be caller-supplied, no executable/library pairing is inferred, and 'zero map flags mean unknown permissions' explains what include_debugger_context does and does not guarantee. That caveat about a falsey/default case is semantics the schema alone does not convey.

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?

The description names a specific verb and resource ('Inspect a supplied Linux ELF64 amd64 little-endian core') with tight scope qualifiers, and immediately contrasts it with what it is not ('without launching its target or attaching to any live PID'). That negative scoping is precisely what separates it from live-debugging siblings, so an agent can differentiate it without opening the schema.

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?

It gives clear conditions for use: you must already have a 'supplied' core, no target is launched, no PID is attached, and no implicit executable/library pairing occurs. It also flags the opt-in path for debugger-derived mappings via 'explicit BYO configuration'. It stops short of naming a concrete alternative tool or a case where you should pick a different sibling, so it is clear context rather than full when/when-not routing.

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

Deploy Server

Other Tools