Crank Protocol

get_source_accuracy

Read-onlyIdempotent

Historical directional hit-rate of each intelligence source (free read).

Returns per-source accuracy stats for the intelligence signal sources (Coin Bureau / YouTube, RSS, Fear & Greed API, on-chain), so an agent can weight a source's calls by how often its bullish/bearish reads have played out. Each source carries a windows map over rolling 7d/30d/90d periods, each with total resolved calls, correct/incorrect counts, and accuracy_pct; sources with no resolved calls yet are omitted, and results are ranked by longest-window accuracy. windows optionally narrows the periods (subset of [7,30,90]); source_type optionally filters by source kind (youtube, rss, api, on_chain). Accuracy = the directional call vs the realised Birdeye price over the prediction window. Past accuracy is not a guarantee. Not financial advice.

Workflow: INTELLIGENCE step -- pair with get_market_briefing to discount or trust a signal by its source's track record before sizing a position.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`windows`	No
`caller_id`	No
`source_type`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive. The description adds behavioral details: sources with no resolved calls are omitted, results are ranked by longest-window accuracy, accuracy calculation method, and disclaimers about past performance. No contradiction with annotations.

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 clear and well-structured: purpose statement, detailed explanation of output structure, parameter descriptions, and workflow guidance. It is somewhat lengthy but each part adds value, so not wasteful.

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?

The description explains the output structure in detail (windows map, periods, counts, accuracy_pct) despite an output schema existing. It covers parameter effects and behavioral nuances. Only minor gap: 'caller_id' not elaborated, but it's a common optional field.

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?

Schema description coverage is 0%, but the description explains 'windows' (subset of [7,30,90]) and 'source_type' (youtube, rss, api, on_chain). The 'caller_id' parameter is not explained, but it appears to be a standard identifier with default empty.

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 'Historical directional hit-rate of each intelligence source' and elaborates with per-source accuracy stats. It distinguishes itself from sibling tools like get_signals or get_source_weights by focusing specifically on historical accuracy.

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 workflow guidance: 'Workflow: INTELLIGENCE step -- pair with get_market_briefing to discount or trust a signal by its source's track record before sizing a position.' It also mentions it's a free read, indicating no cost.

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

All Crank Protocol tools Inspect

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

B3.2/5.0

Disambiguation2/5

Multiple tools overlap significantly: close_perp_position vs perp_close, get_leaderboard vs get_score_leaderboard vs get_strategy_leaderboard, get_venue_status vs get_all_venues_status, send_token_social vs bulk_send_social, and get_crank_score vs get_score. Several read-only tools have nearly identical purposes, and the descriptions do not always clarify boundaries.

Naming Consistency4/5

Most tools follow a consistent verb_noun snake_case pattern (get_balances, create_strategy, set_alert, list_webhooks). However, there are deviations like 'lst_swap', 'jupiter_swap', 'flash_loan', 'sr_backtest', and the use of both 'get_' and 'list_' for reads, plus category prefixes like 'perp_' and 'strategy_' that vary in order. Overall still readable and predictable.

Tool Count1/5

177 tools is an extreme count for any server, far exceeding the 25+ threshold for 'too many'. Even a full DeFi platform does not need this many separate operations; the surface is overwhelming and clearly not well-scoped.

Completeness3/5

The domain (Solana DeFi trading) is covered extensively across swaps, perps, lending, staking, strategies, signals, and support. However, there are notable gaps: no lend_withdraw, no direct way to close a lending position, no spot order cancellation (though aggregator-based swaps may not need it), and a general lack of tiered account management. The huge number of tools makes it hard to identify missing lifecycle steps.

Resources

Need Help?