Skip to main content
Glama

ScoreCompute

by com.scorecompute
OverviewDiscussionsAdmin

run_route_policy

Read-onlyIdempotent

Execute a supplied bounded score AST on 2–128 Euclidean-km points with depot 0 and 2-opt. Validates the closed tour; exact=false. No retraining, external effects or promotion. Hashes identify programs, not independent validation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pointsYes
programYes
fuel_limitNo
time_budget_msNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
legsYes
exactYes
orderYes
fuel_usedYes
length_kmYes
elapsed_msYes
fuel_limitYes
provenanceYes
limitationsYes
stop_reasonYes
kernel_versionYes
program_sha256Yes
simplificationYes
contract_versionYes
initial_length_kmYes
all_points_coincidentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedOutput schema / properties / contract_version / const
      Previous value: -"0.1.0"New value: +"0.2.0"
    • removedOutput schema / properties / fuel_limit / exclusiveMinimum
      Removed value: -0
    • changedOutput schema / properties / fuel_limit / maximum
      Previous value: -9007199254740991New value: +4000000
    • addedOutput schema / properties / fuel_limit / minimum
      Added value: +1
    • changedOutput schema / properties / fuel_used / maximum
      Previous value: -9007199254740991New value: +4000000
    • addedOutput schema / properties / kernel_version
      Added value: +{
+  "const": "1.0.0",
+  "type": "string"
+}
    • addedOutput schema / properties / simplification
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "compiled_program_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "executed_node_count": {
+      "maximum": 31,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "original_node_count": {
+      "maximum": 31,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "original_program_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "required_features": {
+      "items": {
+        "enum": [
+          "distance",
+          "depot",
+          "isolation",
+          "centrality",
+          "progress"
+        ],
+        "type": "string"
+      },
+      "maxItems": 5,
+      "type": "array"
+    },
+    "simplifier_version": {
+      "const": "1.0.0",
+      "type": "string"
+    }
+  },
+  "required": [
+    "simplifier_version",
+    "original_program_sha256",
+    "compiled_program_sha256",
+    "original_node_count",
+    "executed_node_count",
+    "required_features"
+  ],
+  "type": "object"
+}
    • addedOutput schema / properties / stop_reason / enum
      Added value: +[
+  "heuristic_converged",
+  "fuel_exhausted",
+  "time_budget_exhausted"
+]
    • changedOutput schema / required
      Previous value: -[
-  "contract_version",
-  "program_sha256",
-  "order",
-  "legs",
-  "length_km",
-  "initial_length_km",
-  "stop_reason",
-  "fuel_used",
-  "fuel_limit",
-  "elapsed_ms",
-  "exact",
-  "all_points_coincident",
-  "limitations",
-  "provenance"
-]New value: +[
+  "contract_version",
+  "kernel_version",
+  "program_sha256",
+  "simplification",
+  "order",
+  "legs",
+  "length_km",
+  "initial_length_km",
+  "stop_reason",
+  "fuel_used",
+  "fuel_limit",
+  "elapsed_ms",
+  "exact",
+  "all_points_coincident",
+  "limitations",
+  "provenance"
+]
  2. Added

TDQS

B3.4/5.0
Behavior5/5

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

Beyond the read-only and idempotent annotations, the description discloses important behavioral limits: it validates a closed tour, exact=false, performs no retraining, external effects, or promotion, and hashes identify programs but not independent validation. These are non-obvious operational facts an agent needs.

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 definition is compact and front-loaded, moving from execution to validation to operational caveats. Each sentence carries information, though the dense technical vocabulary could be more accessible.

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?

The output schema is present, so return values need not be described. However, for a tool with a deeply nested program parameter and 0% schema description coverage, the description leaves important parameter semantics and AST usage details incomplete.

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

Parameters2/5

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

With 0% schema description coverage and four parameters, the description only partially compensates by mentioning 2–128 Euclidean-km points and depot 0. It does not explain fuel_limit, time_budget_ms, or the semantic meaning of the nested AST fields and feature names.

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?

The description names a specific verb and resource: execute a supplied bounded score AST over Euclidean points using depot 0 and 2-opt. The word "supplied" helps distinguish it from a policy-forging sibling, though the AST jargon keeps it from being fully transparent.

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?

It implies this tool runs a pre-existing program rather than training one, but gives no explicit when-to-use or when-not-to-use guidance. It does not name or compare against siblings such as forge_route_policy or route_optimizer.

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

All ScoreCompute 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