Skip to main content
Glama

Affine Earth Math Court Remote

by earth.affine
OverviewDiscussionsAdmin

game_frame_meta

Run a language-game context and return its state plus the cell's own self-evaluation of the rendered frame - integer score 0-1000 over occupancy, spread, contrast and edge quality, with the C4 span correction applied. Stateless: (kind, seed, t, n, at_seq) fully determine the result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hNodecimal string. e.g. 128
nNodecimal string, population. e.g. 16
tNodecimal string, step index. e.g. 0
wNodecimal string. e.g. 128
kindNothe language-game context kind: atc, proteins or materials, e.g. proteins
seedNodecimal string; JSON numbers still admitted. e.g. 7
at_seqNodecimal string, pinned corpus epoch. e.g. 1
targetNodecimal string, refine until score >= this (0-1000, default 950). e.g. 950
max_iterNodecimal string, iteration cap, default 10. e.g. 10

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / at_seq / description
      Previous value: -"decimal string, pinned corpus epoch"New value: +"decimal string, pinned corpus epoch. e.g. 1"
    • changedInput schema / properties / h / description
      Previous value: -"decimal string"New value: +"decimal string. e.g. 128"
    • addedInput schema / properties / kind / description
      Added value: +"the language-game context kind: atc, proteins or materials, e.g. proteins"
    • removedInput schema / properties / kind / enum
      Removed value: -[
-  "atc",
-  "proteins",
-  "materials"
-]
    • changedInput schema / properties / max_iter / description
      Previous value: -"decimal string, iteration cap, default 10"New value: +"decimal string, iteration cap, default 10. e.g. 10"
    • changedInput schema / properties / n / description
      Previous value: -"decimal string, population"New value: +"decimal string, population. e.g. 16"
    • changedInput schema / properties / seed / description
      Previous value: -"decimal string; JSON numbers still admitted"New value: +"decimal string; JSON numbers still admitted. e.g. 7"
    • changedInput schema / properties / t / description
      Previous value: -"decimal string, step index"New value: +"decimal string, step index. e.g. 0"
    • changedInput schema / properties / target / description
      Previous value: -"decimal string, refine until score >= this (0-1000, default 950)"New value: +"decimal string, refine until score >= this (0-1000, default 950). e.g. 950"
    • changedInput schema / properties / w / description
      Previous value: -"decimal string"New value: +"decimal string. e.g. 128"
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses 'Stateless' and names the exact parameter tuple that determines the result, plus what the returned score measures. However, it says nothing about side effects, prerequisites, cost, or the meaning of 'C4 span correction' or 'cell', leaving real behavioral gaps.

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?

Two tight sentences, front-loaded with the operation and its return semantics, with the statelessness constraint at the end. No padding, though the 'C4 span correction' phrasing assumes insider knowledge and costs clarity for no length benefit.

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?

With no output schema, the description correctly takes on explaining the return value (score 0-1000 over occupancy, spread, contrast, edge quality) and the statelessness contract, which is solid coverage. But with 9 parameters and dense domain jargon, it leaves key concepts (cell, C4 span correction, quality of the frame) undefined for an agent that must invoke it blind.

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 schema already documents all nine parameters and the baseline is 3. The description adds genuine value by naming which parameters (kind, seed, t, n, at_seq) fully determine the result, but leaves h, w, target, and max_iter semantics entirely to the schema.

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+resource ('Run a language-game context') and describes the return payload (state plus a 0-1000 self-evaluation score with C4 span correction), which is more than a restatement of the name. The jargon is dense but the operands and output are named. It doesn't tie itself to a specific sibling like critique_frame, so it stops short of the top tier.

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 when-to-use guidance, no when-not-to-use, and no alternative tools named, despite a large noisy sibling set including critique_frame and other frame/cell tools. The description implies this is the entry point for running a language-game but gives no decision criteria for choosing it over neighbors.

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

All Affine Earth Math Court Remote toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources