Skip to main content
Glama
ismaelsoilet

jev-harness

by ismaelsoilet
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Modulate Reasoning Effort

jev_modulate_reasoning_effort
Read-onlyIdempotent

Calibrate reasoning effort and generation lease steps for the next LLM call, mapping provider parameters to prevent reasoning token waste.

Instructions

Dynamically modulates reasoning effort (low, medium, high, etc.) and generation stability lease steps for the immediate LLM call. Maps provider-specific parameters for OpenAI (GPT-6 Astra/o3), DeepSeek (V4.1-Flash/R1), Qwen (3.8 Max), Anthropic (Claude Fable 5.1), and Gemini (3.8 Thinking) to prevent reasoning token waste.

Use when: Preparing a prompt or tool call for a reasoning-capable LLM to calibrate thinking effort according to task complexity. Do NOT use when: Calling standard non-reasoning models or local deterministic scripts.

Returns: JSON object with 'effort' (string), 'provider' (string), 'provider_params' (object with provider-native kwargs), 'is_reasoning_supported' (boolean), 'cache_safe_recommendation' (string), and 'lease_steps' (integer).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoOptional model identifier to check for direct non-reasoning compatibility.
contextYesThe command, prompt, or next step to evaluate.
providerNoTarget provider dialect (openai, deepseek, qwen, anthropic, gemini, kimi, mimo). Default: openai.openai
max_lease_stepsNoOptional upper bound for generation stability lease steps (default: 10).
supported_effortsNoOptional list of supported effort levels (e.g. ['none', 'minimal', 'low', 'medium', 'high', 'xhigh', 'max', 'ultra']).
session_context_tokensNoOptional active prompt tokens in session context to evaluate prompt cache risk.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.2.2
    • addedInput schema / properties / max_lease_steps / default
      Added value: +10
    • addedInput schema / properties / max_lease_steps / maximum
      Added value: +50
    • addedInput schema / properties / max_lease_steps / minimum
      Added value: +1
    • addedInput schema / properties / provider / default
      Added value: +"openai"
    • changedInput schema / properties / provider / description
      Previous value: -"Target provider (openai, deepseek, qwen, anthropic, gemini, kimi, mimo). Default: openai."New value: +"Target provider dialect (openai, deepseek, qwen, anthropic, gemini, kimi, mimo). Default: openai."
    • addedInput schema / properties / provider / enum
      Added value: +[
+  "openai",
+  "deepseek",
+  "qwen",
+  "anthropic",
+  "gemini",
+  "kimi",
+  "mimo"
+]
    • addedInput schema / properties / session_context_tokens / default
      Added value: +0
    • addedInput schema / properties / session_context_tokens / minimum
      Added value: +0
  2. First observedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description goes beyond them by listing the exact return payload fields and the provider dialects handled, though it does not explain what 'generation stability lease steps' actually do (e.g., whether the lease is consumed elsewhere).

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?

Front-loaded with the core action, then cleanly segmented into 'Use when / Do NOT use when / Returns'. The embedded provider list is somewhat verbose but informative, and every section earns its place.

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?

With no output schema, the description usefully enumerates the return fields, and usage/return semantics are covered. Minor gaps remain in explaining the meaning of 'lease_steps' and 'cache_safe_recommendation' as domain concepts, but an agent has enough to invoke it correctly.

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 six parameters are already documented, including the effort-level example list. The description adds only the general notion of provider dialects and effort grading, mostly redundant with the schema, so baseline 3 is appropriate.

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?

States a specific verb ('modulates') and resource ('reasoning effort' and 'generation stability lease steps') and explains the effect (mapping provider-specific params to prevent token waste). This is unambiguous and clearly distinct from the orchestration siblings like jev_route_task or jev_check_abort.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicit 'Use when' (preparing a prompt/tool call for a reasoning-capable LLM, calibrating effort to task complexity) and 'Do NOT use when' (non-reasoning models, local deterministic scripts) clauses. Nothing is left to inference about when this tool applies.

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