Skip to main content
Glama

Affine Earth Math Court Remote

by earth.affine
OverviewDiscussionsAdmin

critique_frame

Grade a rendered frame and return integer corrections. THE CRITIC IS DETERMINISTIC, NOT A MODEL: nine cells must reach the same verdict or the fleet's byte-identity is gone, and a cell reports generative:0 because it hosts no model. Scores 0-1000 and returns span/pitch deltas as integers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hNodecimal string. e.g. 128
nNodecimal string. e.g. 16
tNodecimal string. e.g. 0
wNodecimal string. e.g. 128
kindNothe language-game context kind: atc, proteins or materials, e.g. atc
seedNodecimal string; JSON numbers still admitted. e.g. 7
span_scale_q16Nodecimal string, framing to grade; 65536 = unity. e.g. 65536

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • 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. atc"
    • removedInput schema / properties / kind / enum
      Removed value: -[
-  "atc",
-  "proteins",
-  "materials"
-]
    • changedInput schema / properties / n / description
      Previous value: -"decimal string"New value: +"decimal string. 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 / span_scale_q16 / description
      Previous value: -"decimal string, framing to grade; 65536 = unity"New value: +"decimal string, framing to grade; 65536 = unity. e.g. 65536"
    • changedInput schema / properties / t / description
      Previous value: -"decimal string"New value: +"decimal string. e.g. 0"
    • changedInput schema / properties / w / description
      Previous value: -"decimal string"New value: +"decimal string. e.g. 128"
  2. First observed

TDQS

B3.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: the critic is deterministic, requires nine-cell consensus, and reports generative:0 for model-less cells. It also describes the return payload (score 0-1000, integer span/pitch deltas). It omits permissions, side effects, and failure behavior, keeping it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, which is good. However, the middle sentence is dense and jargon-heavy ('nine cells must reach the same verdict or the fleet's byte-identity is gone'), and the capitalized clause reads as shouting rather than clear exposition.

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?

No output schema exists, so the description must explain return values, and it does so partially (0-1000 score, integer deltas). But for a 7-parameter tool the description never maps the cryptic h/n/t/w/kind/seed params to their role, and it is silent on the meaning of 'corrections' downstream.

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 seven parameters, setting the baseline at 3. The description adds only indirect hints (span/pitch deltas maps loosely to span_scale_q16; 'framing to grade' hints at t and span), but explains no parameter meaning beyond 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: 'Grade a rendered frame and return integer corrections.' An agent can tell this critiques/grades a frame rather than generating or verifying one, and no sibling tool overlaps with frame grading. It stops short of distinguishing itself explicitly from ambiguous neighbors like game_frame_meta.

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?

No when-to-use guidance, no prerequisites, and no named alternative. The determinism/byte-identity constraint is stated as a trait, not as a condition that selects this tool over another. The agent is left to infer when a frame should be critiqued.

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