Skip to main content
Glama

studio_knowledge

Read-onlyIdempotent

Ask the studio's knowledge graph a question in a trader's words (how do I backtest, what does C039 mean, the Pine twin of ta.crossover, what comes after the gate). It answers the nodes that hold the rule: cubicle.script concepts, the runner's functions, series and truths with their Pine names, every diagnostic code, every studio tool, the seven desk steps, the templates and our research scripts with their evidence. Each node carries act: the tool (with arguments) or the deck place that does it, so take that action next instead of describing it. Pass id (fn:ema, code:C039, step:gate) for one node. Read only, free, needs no sign-in.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "studio_knowledge"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNohow many nodes (1 to 10, default 5)
qNothe question, in the trader's words
idNoone node id instead, such as fn:ema, code:C039, concept:gate or step:practice

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new facts beyond those: 'free' (no cost) and 'needs no sign-in' (no auth prerequisite), plus the important disclosure that each returned node carries an `act` field naming a tool-with-arguments or deck place. What it omits is failure behavior — what happens when no node matches, or whether `q` and `id` are mutually exclusive.

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 purpose is front-loaded in the first clause, followed by scope, then parameters, then constraints — a sensible order with no filler sentences. The middle sentence is a long run-on enumeration of node categories ('cubicle.script concepts, the runner's functions, series and truths…'), which is informative but denser than needed. Still, every clause maps to real scope rather than padding.

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

Completeness4/5

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

With no output schema, the description takes on responsibility for the return contract and does so by explaining that nodes carry an `act` field with tool-plus-arguments. Combined with the query examples and the no-sign-in/no-cost note, an agent has enough to call this correctly. The remaining gap is edge-case behavior on empty results and the `q`-vs-`id` interaction.

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 three parameters including the id examples (fn:ema, code:C039, concept:gate, step:practice) and the 1–10 default for `k`. The description restates the `id` examples without adding new semantics such as precedence between `q` and `id`, or whether `k` is ignored when `id` is supplied. Baseline 3 is appropriate when the schema carries the load.

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 opens with a specific verb and resource: 'Ask the studio's knowledge graph a question in a trader's words,' then enumerates the exact content domain (diagnostic codes, runner functions, Pine names, desk steps, templates). An agent immediately knows this is a lookup/QA tool rather than a trading or charting action. It stops short of 5 because no sibling is named as a contrast (e.g., how this differs from `catalogue` or `desk_read`), so differentiation must be inferred from scope.

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

Usage Guidelines4/5

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

Usage is well-contextualized: example questions ('how do I backtest', 'what does C039 mean') show the intended shape of a call, and 'Pass `id` … for one node' tells the agent when to use the id path instead of `q`. It also gives a follow-up rule — 'take that action next instead of describing it' — which steers downstream behavior. There are no explicit exclusions or named alternative tools, keeping it below 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources