Skip to main content
Glama

Affine Earth Math Court Remote

by earth.affine

execute_artifact_crucible

Ingest an ARTIFACT INGESTION BRIEF plus the artifact an agent generated for it; evaluate it against the laws the brief declares; seal and return the artifact ONLY on the top rung. Headless by construction - a CI runner, a curl script, an autonomous agent and an editor all post the identical tools/call, because enforcement lives at the API layer and a frontend cannot bind a caller who does not use one. The brief is the single home for the target architecture; a target_architecture argument that contradicts it is REFUSED_ARCHITECTURE_CONFLICT rather than silently overriding it. Verdicts are a ladder, not a coin: CALORIE_AFFINE_ARTIFACT_DELIVERED / ARTIFACT_ASSEMBLED_NOT_DELIVERED / ARTIFACT_WIN_UNVERIFIABLE / ARTIFACT_PROTOCOL_CONTRADICTED / ARTIFACT_TARGET_ABSENT / ARTIFACT_LAW_BROKEN / NOT_KNOWN, with qmt_verdict WIN|MISS derived from the rung for callers who want one bit. A host with no toolchain returns REFUSED_NO_CRUCIBLE_HOST and NO qmt_verdict at all - nothing was judged, and reporting MISS would claim the geometry failed when the brief never reached the geometry.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
briefYesThe complete ARTIFACT INGESTION BRIEF: four sections ([LANGUAGE GAME DEFINITION], [STRUCTURAL GOAL], [PAYLOAD SHAPE], [WASM MEMBRANE INTEGRATION]) with every field filled. The blank template is refused as REFUSED_UNFILLED_PLACEHOLDER.
artifactYesThe source the agent generated to satisfy the brief. Generation is the caller's half; the crucible compiles, evaluates and seals.
target_architectureNoOPTIONAL and redundant: the brief's [PAYLOAD SHAPE] is the single home for this value. Supplied only for callers using the original schema; a value that contradicts the brief is REFUSED_ARCHITECTURE_CONFLICT rather than silently overriding it.

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden, and it is exceptionally transparent. It discloses that the tool only seals and returns on the top rung, that a target_architecture conflict is refused rather than silently overridden, and that a missing toolchain produces no qmt_verdict at all.

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?

The description is dense and front-loaded, opening with the core ingest-evaluate-seal behavior before covering edge cases. It is not short, but every sentence carries operational or protocol information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description enumerates the full verdict ladder, the derived qmt_verdict, the no-toolchain refusal path, and the target_architecture conflict behavior. This gives an agent the critical response and edge-case context needed to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds meaning by clarifying that target_architecture is optional/redundant, that the brief is the single home for architecture, and that artifact generation is the caller's responsibility. This is useful, but the description does not deeply elaborate the format expectations beyond what the schema already provides.

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?

The description states a specific verb-resource pair: ingest an ARTIFACT INGESTION BRIEF plus generated artifact, evaluate it against the declared laws, and seal/return it only on the top rung. This clearly differentiates the tool from the many verify_* sibling tools by tying it to the brief-and-artifact evaluation workflow.

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 description gives useful contextual guidance: generation is the caller's half, headless callers all post the same call, and a host without a toolchain yields REFUSED_NO_CRUCIBLE_HOST. However, it never explicitly states when to choose this tool over alternative execute_* or verify_* siblings, so selection remains largely implicit.

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
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.6/5.0
Disambiguation2/5

Many verify_* tools are distinct, but there are overlapping clusters: math_court duplicates execute_2local_hamiltonian, route_spin_glass_manifold, and the quantum verifiers; project_affine_key, expose, verify_presented_pair, and the optional affine exposes in other tools blur together; weather and geometry tools also overlap. The detailed descriptions help a human, but an agent would likely struggle to choose between equivalent-seeming entry points.

Naming Consistency2/5

Naming is mostly snake_case but otherwise inconsistent: some tools use dotted prefixes (atc.*, twin.robotics.*, weather.*), some use bare verbs (expose, lattice_op, math_court), some use noun phrases (corpus_bonds, feeds_catalog), and others mix prefixes with verbs (ide_rebuild_mesh, umc_resume). The verify_* family is consistent, but the overall set has no single predictable verb_noun pattern.

Tool Count2/5

49 tools is far above the typical well-scoped server size and includes multiple near-duplicate paths to the same law (math_court, execute_*, route_*, verify_*). While not quite 50+, the count still feels like a sprawling kitchen-sink rather than a deliberate minimal surface.

Completeness3/5

The toolset covers a surprisingly wide range: QC verifiers, QMA laws, affine projections, corpus reads, weather, UMC state, and robotics IK. However, there are notable gaps for such a broad surface: no general court case lifecycle beyond expose/seal, no corpus content search, and no way to manage or update sealed artifacts; several areas have only entry-point coverage.

Resources