Skip to main content
Glama

thanaton_speculate_race

Runs multiple candidate code patches in parallel ephemeral microVMs, commits the first passing candidate, and terminates losers to accelerate speculative branch testing.

Instructions

Execute multi-candidate speculative branch racing: runs N candidate code patches in parallel ephemeral microVMs, commits the fastest passing candidate, and instantly reaps losers.

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": {
      "candidates": "<candidates>"
    },
    "name": "thanaton_speculate_race"
  }
}

Input Schema

NameRequiredDescriptionDefault
candidatesYesList of candidate hypotheses/patches to race in parallel
problem_idNoUnique identifier for the task or problemdefault_problem
timeout_msNoMaximum race timeout in milliseconds

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?

With no annotations, the description carries the burden and does disclose meaningful behavior: parallel ephemeral microVMs, a commit of the winner, and reaping of losers — implying mutation and destruction of non-winning state. It does not say where 'commits' applies (repo vs. filesystem vs. sandbox), what happens if no candidate passes or the timeout fires, or whether the race consumes billable resources.

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 filler, and the core mechanics arrive in the right order (race → commit → reap). Slightly jargon-dense but every clause earns its place.

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?

There are no annotations and no output schema, so the description is the only source of behavioral truth for a mutating, resource-spawning tool. It explains the race mechanic but omits outcome reporting (winner ID, logs, exit codes) and the no-passing-candidate/timeout edge cases an agent needs to interpret results.

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 the nested candidate fields (id, code, command, language) and problem_id/timeout_ms are already documented. The description adds only the 'N candidates' framing and the 'fastest passing' selection criterion, without clarifying timeout semantics or how problem_id scopes results.

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?

Specific verb+resource: 'Execute multi-candidate speculative branch racing' with concrete mechanics (N patches in parallel microVMs, fastest passing candidate committed, losers reaped). This clearly separates it from single-execution siblings like thanaton_run_code, though no sibling is named 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?

The 'N candidate patches' framing implies the use case (you have multiple hypotheses and want the fastest working one), but there is no explicit when-to-use/when-not statement and no pointer to run_code or exec_command for the single-candidate case.

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