Skip to main content
Glama

Backtesting Arena

by io.github.Schoasch

Get Chart Image (PNG) for a platform series

arena_get_chart

Renders one of the named platform series as a PNG line chart and returns it as an MCP image content block, plus a JSON meta block. The chart INHERITS the freedom of the data tool: it calls the same delivery layer, so it shows exactly the points the corresponding data tool would return for your tier — no finer resolution, no other source; the optional days parameter narrows the window under the same tier cap. The image itself carries n, the read date range, the gap count, a warning line when the window was capped, the mandatory source attribution where the series requires one, and the platform watermark — these survive a screenshot on purpose: a chart built from nine points says n=9 in the picture. For the underlying numbers call the matching data tool (e.g. series=kimchi_premium ↔ arena_get_kimchi_premium). Descriptive rendering, never a signal. [Free tier · window depth follows your tier]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoWindow in days, capped by tier exactly like the matching data tool; the image names any cap.
seriesYesWhich series to render. Start set — the matching data tool names the semantics.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations are absent, so the description carries full burden. It discloses the chart inherits the data tool's freedom, shows exactly the same points for the tier, has a tier cap for the days window, includes n, date range, gap count, warning line, attribution, and watermark in the image, and explicitly states it is never a signal. No contradictions with annotations since none exist.

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 description is longer than a typical one-liner, but each sentence adds meaningful context: purpose, tier inheritance, image contents, connection to data tools, and the 'never a signal' disclaimer. It is front-loaded with the purpose and well-structured, though it could be slightly leaner without losing value.

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?

For a 2-param tool with no output schema, the description is comprehensive: it explains the return format, the content of the image, the tier behavior, and how to get underlying numbers. It even gives an example mapping. Nothing critical is missing for an agent to correctly invoke and interpret this tool.

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

Parameters4/5

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

The schema already provides 100% coverage of both parameters. The description adds the tier-cap behavior for days and clarifies that series semantics are given by the matching data tool. It also notes the image names any cap, which is extra context beyond the schema, but the core parameter meaning is already in the 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 clearly states the tool renders a platform series as a PNG line chart and returns it as an MCP image content block plus a JSON meta block. It distinguishes this from data tools by explicitly naming the matching data tool for underlying numbers, so an agent can tell it apart from siblings like arena_get_kimchi_premium.

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?

It explicitly tells the agent when to use this tool (when a chart is needed) versus the matching data tool (when underlying numbers are needed). It also clarifies that the chart is descriptive, never a signal, and notes the tier cap behavior, which informs decision-making.

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

All Backtesting Arena 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

A3.6/5.0
Disambiguation2/5

Many tools cover overlapping market indicators (e.g., cycle state, pulse, bullmarket ampel, volatility phases) and several share similar get_*_history patterns, which could cause an agent to select the wrong one. However, each tool has detailed descriptions with explicit references to related tools to reduce ambiguity.

Naming Consistency3/5

Tool names generally follow a verb_noun pattern (arena_get_*, arena_list_*, arena_run_*, arena_subscribe_*), but there are inconsistencies such as 'validate_strategy' (no arena_ prefix), 'arena_status' (not a clear verb_noun), and variations like 'arena_run_grid_backtest' vs 'arena_run_backtest'.

Tool Count2/5

With 84 tools, the server is heavily over-scoped for a typical MCP server, likely causing navigation and selection overhead. While the domain (crypto backtesting and analytics) is broad, 84 tools exceed reasonable coherence and impose a high cognitive load.

Completeness4/5

The tool surface covers a wide range of analytics (market indicators, backtesting, validation, alerts, subscriptions, reports) with few obvious dead ends. Minor gaps exist like lack of direct portfolio management or strategy editing, but core workflows are well covered.

Resources