Skip to main content
Glama

eschaton_complexity_profile

Profiles C/C++ algorithms by counting guest instructions with Valgrind Lackey to determine runtime growth and prove O(N) versus O(N²) complexity without CPU jitter.

Instructions

Deterministic cycle and instruction counter via Valgrind Lackey: measures exact guest instruction counts to mathematically prove O(N) vs O(N^2) complexity immune to CPU jitter.

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_complexity_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNoStandard input for algorithm100
language_idNoC or C++ language ID (e.g. 50, 54, 201, 202)
source_codeYesC/C++ algorithm source code to profile

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

B3.4/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It usefully discloses the mechanism (Valgrind Lackey) and the determinism guarantee, but omits practical traits such as slow execution under instrumented runs, compile/runtime failure behavior for bad C/C++, and what the caller receives back.

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 dense sentence, front-loaded with the mechanism and the measurement it produces. The phrase 'mathematically prove O(N) vs O(N^2)' is slightly promotional but still conveys the intended analytical use.

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 tool with no output schema and no annotations, the description should say more about what comes back (instruction counts, cycle estimates, or a complexity verdict) and how stdin relates to the O(N) comparison. It is adequate to understand intent but leaves interpretation gaps.

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 (stdin, language_id, source_code) are already documented in the schema. The description adds no extra meaning about input format, expected program behavior, or how stdin drives the scaling measurement, so the baseline of 3 applies.

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 gives a specific verb and resource: counting guest instruction cycles via Valgrind Lackey to classify algorithmic complexity. It clearly distinguishes the tool from timing-based profiling siblings by emphasizing determinism, though it never names an alternative tool explicitly.

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 only implied: the mention of 'mathematically prove O(N) vs O(N^2)' and 'immune to CPU jitter' signals the scenario (rigorous complexity comparison rather than wall-clock benchmarking). There is no explicit when-to-use vs when-not guidance or reference to sibling tools like eschaton_fast_batch.

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