Skip to main content
Glama

decker

by io.github.gigshow

decker.get_market_state

Market State v0 — current engine structural state for a symbol/timeframe (latest evaluated bar, persisted engine emit read as-is, zero recompute). DOMAIN FRAME (why this engine exists): the market is read as a TARGET GAME — every coordinate comes from a verified anchor (a past level where a triggered move actually succeeded). The game block tells you the context that matters: game.status = forming_target (new anchor set, awaiting test) | testing_target (price is testing whether the declared target holds) | direction_resolved (game decided, price traveling); game.target = WHO is being judged (anchor id/phase/band); game.progress_dest = where price goes if the move proceeds (the opposing verified anchor to conquer); game.reverse_dest = where it goes if the move fails (the opposite house — also the stop logic's home); game.why_gate = full gate derivation chain; game.zt_regime = output canonicality (restored = deterministic delta lineage). action_gate alone (GO/WATCH/HOLD) is only a posture — the game context is the information. RAW CONTRACT: fields are engine-native vocabulary (c_state, hold_reason, R_* risk enums …), NOT customer-facing prose — for a human-language view use decker.get_view (with tf) or decker.get_reading. layer=STATE: this is a market-state reading, NOT a trade instruction. Absent fields are null (engine did not emit that axis — no filling). IMPORTANT: top-level state.c_state/action_gate/trigger_kind reflect the TRIGGER SNAPSHOT (only populated on a bar that actually had a trigger event) — null on most bars is normal, not a data gap. For the always-present, every-bar-populated view of the same axes use game.phase.c_state / game.phase.action_gate instead (different freshness, same underlying engine state machine). Don't read a null top-level field as 'engine has no state' — check game.phase first. object_context (top-level, W1-C1 standard object block, present when a recent trigger bar exists): my_anchor/opp_anchor(reversal destination)/judgment_ref/geometry/why(engine reason_codes)/reverse_branch context (object_context.reverse_direction_conflict is present only when a local reversal shows stage='confirmed' but the swing's confirmed direction still disagrees — read it before treating reverse_branch.stage='confirmed' as a swing-level reversal). null on non-trigger bars or symbols outside the narrative universe (e.g. individual KRX stocks). Before placing any order through any execution tool, check the intent with decker.validate_intent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYese.g. BTCUSDT
timeframeYes

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so extensively. It explains that the tool reads as-is with zero recompute, that absent fields are null (no filling), and that top-level c_state/action_gate are only populated on trigger bars — null on most bars is normal. It also details the object_context presence conditions. This provides deep transparency about what the tool returns and when fields are null. Some aspects like error handling or rate limits are omitted, but for this data-fetching tool the behavioral contract is well covered.

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

Conciseness3/5

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

The description is extremely long and verbose, packing in a full conceptual framework (DOMAIN FRAME, RAW CONTRACT, layer explanations, IMPORTANT notes). While the first sentence delivers the core function immediately, much of the subsequent text is detailed context that, while valuable, could be trimmed or moved elsewhere. It is structured with clear headings, which aids readability, but it is not concise. It does not waste space on fluff, but its sheer length pushes it below a high score.

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?

Given the tool's complexity — no output schema, multiple nested contexts (game, object_context), and null-propagation nuances — the description is remarkably complete. It explains the game block semantics, distinguishes top-level vs game.phase freshness, reveals the object_context trigger conditions, and points to related tools. An agent has everything needed to interpret responses and call the tool correctly without additional reference. This is a model of completeness for a complex data tool.

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?

The description mentions 'symbol/timeframe' in the first line, echoing the schema. It does not add additional semantic detail about parameter usage, formats, or dependencies. The schema already provides an enum for timeframe and an example for symbol, giving 50% coverage. The description adds minimal value beyond that, but the parameters are simple and self-explanatory. Baseline 3 is appropriate given the already adequate schema.

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 opens with a precise, specific statement: 'current engine structural state for a symbol/timeframe' — a clear verb+resource. It distinguishes itself from sibling get_view and get_reading by explicitly stating it returns raw engine vocabulary, not customer-facing prose. The tool's purpose is unambiguous and differentiated.

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?

The description provides explicit usage guidance: it states when to use this tool (for raw engine state) and when not to (for human-language views, use decker.get_view or decker.get_reading). It also warns to check decker.validate_intent before placing orders, indicating the contextual role of this tool in a wider workflow. This is direct and actionable.

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
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

A4.3/5.0
Disambiguation3/5

Execution and settings tools are clearly separated, but there is a dense cluster of analytical getters (get_view, get_reading, get_signals, get_assembly) that all return market verdicts and coordinates; their boundaries are only clear after reading the long descriptions. get_market_state versus get_state_timeline is cleaner, but the overlap among the analysis-verdict tools could still cause misselection.

Naming Consistency5/5

All tools share the decker_ prefix and a consistent snake_case verb_noun pattern (get_* for reads, place_order/close_position/update_protective_stops/set_skill_overlay/validate_intent for actions). There is no mixing of naming conventions or vague generic verbs.

Tool Count5/5

Thirteen tools is within the ideal well-scoped range for an execution-plus-analysis server. Each tool maps to a distinct responsibility (state reading, timeline history, signals, execution, position management, user settings, pre-trade validation), so none feels like filler.

Completeness4/5

The lifecycle is well covered: validate_intent → place_order → get_positions → update_protective_stops → close_position, with signal/analysis and skill-overlay tools around it. Minor gaps like a dedicated account-balance or full order-history tool are absent, but the execution engine handles caps server-side and closed round-trips are included in get_positions.

Resources