esp-runtime-mcp

read_coredump

Decode ESP-IDF core dumps from flash, a file, or the last captured UART log to identify the crashed task and return stack frames plus the full report.

Instructions

Run esp-coredump info_corefile and return the crashed task, its stack frames and the full report.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_coredump"
  }
}

Input Schema

Name	Required	Description	Default
`elf`	No
`port`	No
`source`	No	'flash' (needs port), 'file' (needs core_file) or 'last_capture' (UART core dump in the last captured log)	flash
`core_file`	No
`project_dir`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 29, 2026

TDQS

C2.9/5.0

Behavior3/5

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

With no annotations at all, the description carries the full disclosure burden. It does well to say the tool shells out to esp-coredump info_corefile and returns the crashed task, stack frames, and full report before truncation, but it says nothing about connection requirements, failure modes, timeouts, or whether any device state is touched.

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?

A single front-loaded sentence with no wasted clauses. It's efficient, though for a 5-parameter tool with sparse schema coverage a sentence or two more would have earned its place.

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?

A multi-source coredump reader with five optional parameters, no required fields, no annotations, and no output schema needs more than one sentence. The critical source/port/core_file interdependencies and the fact that 'flash' requires a port are entirely absent.

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 coverage is only 20% – just the 'source' field is documented – and the description adds nothing about elf, port, core_file, or project_dir. An agent cannot infer from the prose that port pairs with source=flash, or that core_file is required for source=file; the one implied hint is the literal 'info_corefile' command name.

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?

States a specific verb (read) and resource (coredump) and enumerates what comes back: crashed task, stack frames, full report. It also names the underlying command (esp-coredump info_corefile), which pins the behavior precisely. It doesn't explicitly differentiate from siblings like analyze_log or decode_addresses, so it falls 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 Guidelines2/5

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

There is no guidance on when to reach for this tool versus analyze_log, decode_addresses, or capture_log, and no prerequisites such as needing a connected device or the esp-coredump utility installed. The only selection logic exists in the schema's 'source' field, not the description.

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

Deploy Server