Skip to main content
Glama

decker

by io.github.gigshow
OverviewDiscussionsAdmin

decker.get_price_axis_state

[DEPRECATED — use decker.get_market_state (CR1); this raw price-axis dump is superseded and will be removed after usage telemetry shows zero calls.] Price-axis (close-based target selection) state, read from engine_bar_state as persisted (Store-Output-Read, no recomputation). One voice: signal is the current state — side (+ buy / - sell), the signal bar (judgment bar '2' sealed by S) with its low/high, entry candidates (target, close two bars before the signal, bar-2 open, bar-2 close), and the outcome stated as WHAT crossed WHAT: status 'confirmed' = a close beyond the signal-bar edge in the signal's direction (resolved_ts, resolved_close), 'failed' = beyond the opposite edge, 'inside' = 판정보류 (close still inside the signal bar). prev/history = earlier signals with the same fields. active_target = the target this unit is labeling from (price, touch_kind, touched_ts); label = this bar's labeler output (t1/t2/1/2/+S/-S); pending_targets/rolling_target/conn_stems = coordinates. goal = exit target measured from the entry (signal bar-2 open): nearest opposite confirmed-signal edge at least 2% away, plus ladder = nearest such level at >=2% / >=4% / >=8% from entry (empty tier = no structure there, never filled with a percentage); goal.price null + reason = no level >=2% from entry. event_flow = the persisted event history (oldest→newest, last 20): target_selected / signal / signal_resolved (signal bar confirmed/failed with the close that decided it) / conn_arrival — compare the current state against how the events flowed. Omit timeframe for the multi-timeframe view: one row per TF {readable, target, signal, close} — side by side, no cross-TF verdict (cross_tf_verdict stays null). IMPORTANT — action_gate is always null BY DESIGN: this axis is diagnostic-only and not wired to any gate or order path. For GO/WATCH/HOLD use decker.get_market_state (MAIN axis). null when the engine has not evaluated the symbol/TF.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYese.g. BTCUSDT
timeframeNoOMIT for the multi-timeframe view (all TFs side by side) — that is the intended way to read this axis. Pass one TF only when you deliberately want a single horizon.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / timeframe / description
      Added value: +"OMIT for the multi-timeframe view (all TFs side by side) — that is the intended way to read this axis. Pass one TF only when you deliberately want a single horizon."
    • changedInput schema / properties / timeframe / enum
      Previous value: -[
-  "30m",
-  "1h",
-  "4h",
-  "8h",
-  "1d"
-]New value: +[
+  "30m",
+  "1h",
+  "4h",
+  "8h",
+  "1d",
+  "1w"
+]
    • changedInput schema / required
      Previous value: -[
-  "symbol",
-  "timeframe"
-]New value: +[
+  "symbol"
+]
  2. Added

TDQS

A4.6/5.0
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 does so: it discloses the read source (no recomputation), the diagnostic-only nature, that action_gate is null by design and not wired to any gate/order path, that the result is null when the engine hasn't evaluated the symbol, and the full deprecation lifecycle.

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?

Being dense and front-loaded with the deprecation notice is correct, and each field bundle (signal/prev/history, goal, event_flow) earns its place. It is nonetheless a very long block for a deprecated tool, and the read would be faster split into return-field prose plus a short deprecation line.

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, so the description must explain return values, and it covers signal states (confirmed/failed/inside), goal/ladder semantics, event_flow contents, and the null case comprehensively. Nothing an agent needs to interpret or safely avoid this axis is missing.

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 both parameters are already documented — including the 'omit for multi-TF view' guidance, which the description merely echoes. The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource — a persisted read of 'price-axis (close-based target selection) state' from engine_bar_state — and explicitly names its replacement sibling (decker.get_market_state, CR1). An agent can immediately distinguish it from the MAIN-axis market_state tool.

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

Usage Guidelines5/5

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

Explicitly says the tool is superseded and should be replaced by get_market_state, gives the migration reason (CR1), and states the removal condition (zero-call telemetry). It also tells the agent the intended invocation pattern (omit timeframe for the multi-TF view) and routes GO/WATCH/HOLD queries to the MAIN axis instead.

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

All decker toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources