Skip to main content
Glama

eschaton_sanitize_check

Run AddressSanitizer and UndefinedBehaviorSanitizer checks on C/C++ source code to detect buffer overflows, memory leaks, and use-after-free bugs.

Instructions

Sub-20ms AddressSanitizer (ASan) + UndefinedBehaviorSanitizer (UBSan) safety check: detects buffer overflows, memory leaks, and use-after-free bugs.

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": {
      "source_code": "<source_code>"
    },
    "name": "eschaton_sanitize_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNoStandard input
language_idNoC or C++ language ID (e.g. 50, 54, 201, 202)
source_codeYesC/C++ source code to sanitize

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description must carry the full behavioral burden; it does disclose the detection categories, the sanitizer engines, and a speed characteristic. However, it never states whether the code is compiled and executed (relevant given the stdin and language_id parameters), what limitations or false negatives exist, or what the result looks like — and there is no output schema to cover that.

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?

A single dense sentence with the core action, the engine names, and the detected bug classes front-loaded. No filler and nothing buried.

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

Completeness3/5

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

For a three-parameter tool with no annotations and no output schema, the definition covers what is checked but not how it runs or what it returns. An agent knows the purpose but must discover the response shape and execution model empirically.

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

Parameters3/5

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

Schema description coverage is 100%, so all three parameters are already documented in the schema, making a baseline of 3 appropriate. The description adds nothing about how language_id interacts with the sanitizer check or how stdin is fed to the program.

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 and resource — a sanitizer safety check — and enumerates the exact bug classes it targets (buffer overflows, memory leaks, use-after-free) plus the underlying ASan/UBSan tooling. It does not distinguish itself from siblings like eschaton_preflight_check or eschaton_complexity_profile, which an agent would need to choose between.

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 explicit when-to-use guidance, no exclusion criteria, and no named alternative. The 'Sub-20ms' latency claim implicitly suggests it suits fast or repeated checks, but the agent is left to infer that rather than being told when to prefer this over the preflight or complexity tools.

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