Skip to main content
Glama
Sign In
Cortex Intelligent

Cortex Intelligent

by adyoi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

model_decision

Determines task tier, risk level, routing, and whether verification is needed so an MCP client can choose model behavior and guardrails for a given task.

Instructions

Internal model decision: tier/risk/route/needsVerify.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "model_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYes
filesNo
modelNo
project_rootNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.0
    • addedInput schema / properties / project_root
      Added value: +{
+  "maxLength": 4096,
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

D1.3/5.0
Behavior1/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing: not whether it invokes an LLM (latency/cost), whether it persists state, what it returns, or any side effects. For a tool named 'model_decision' that may make a model routing choice, this opacity is a serious gap.

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

Conciseness2/5

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

It is short and front-loaded, but this is under-specification rather than conciseness; the fragment is too compressed to convey meaning, and the colon-separated field list is not self-explanatory.

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

Completeness1/5

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

With no annotations, no output schema, no enum hints, and zero parameter documentation, the description leaves everything an agent would need — purpose, when to use it, argument meaning, and the shape of the result — unspecified.

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

Parameters1/5

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

Four parameters (task, files, model, project_root) with 0% schema description coverage, and the description mentions none of them and adds no meaning. The agent must guess what 'files' and 'model' do — filter candidates, override the choice, or supply context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Internal model decision: tier/risk/route/needsVerify' restates the tool name and lists possible output fields rather than stating a verb and resource. It never says what the tool actually does (classify a task? pick a model? produce a routing decision?), and it does not distinguish itself from the sibling decision_classify or detect_model.

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

Usage Guidelines1/5

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

There is no guidance on when to call this versus decision_classify, detect_model, get_model_profile, or self_critique. The single word 'Internal' weakly implies it is not meant for direct user invocation but gives no condition, prerequisite, or alternative.

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