Crank Protocol

intelligence_suggestion_approve

Destructive

Approve a StrategySuggestion, optionally creating the suggested Strategy.

Closes the PROPOSE loop for MCP-only agents: wraps the same approve-and-create service logic as the REST StrategySuggestionViewSet.approve action instead of a manual suggested_config round-trip through the strategy create tools, which silently drops the suggestion linkage (StrategySuggestion.created_strategy / hive DecisionRecord.suggestion FK provenance). wallet_address is the caller's own wallet (recorded as approved_by_wallet); when agent_wallet_id also resolves to a wallet wallet_address controls, the suggested Strategy is created through the same executor dry-run gate as every other create path. config_overrides merges over suggested_config (e.g. a real usd_per_buy). A wallet without a Turnkey signer still gets the strategy -- paper trade, unsigned tx per tick. Informational rationale only (rules 5-8); the created strategy still runs only through the existing engine gates.

Workflow: DECIDE -> EXECUTE step -- the MCP-only closing move for get_strategy_suggestions; pair with backtest_strategy + get_risk_assessment first for the same guardrails any other create path gets.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`caller_id`	No
`suggestion_id`	Yes
`wallet_address`	Yes
`agent_wallet_id`	No
`config_overrides`	No
`interval_seconds`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.8/5.0

Behavior5/5

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

Beyond annotations, the description discloses substantial behaviors: the tool records the caller's wallet as 'approved_by_wallet', creation passes through the 'executor dry-run gate', 'config_overrides merges over suggested_config', and wallets without a Turnkey signer still produce a paper-trade strategy. It also clarifies that the created strategy is still governed by existing engine gates.

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 front-loaded with a clear one-sentence summary, then expands into necessary workflow and behavioral details. It is lengthy, but each major clause adds distinguishing context about provenance, dry-run gating, wallet behavior, and guardrails, so the length is earned rather than redundant.

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 mutation tool with complex approval+create semantics, the description covers purpose, relationship to suggestion tools, execution guards, provenance preservation, and the wallet edge case. An output schema is present, so return value details do not need to be repeated in prose, and the description provides enough context for an agent to invoke the tool correctly.

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?

With 0% schema description coverage, the description carries the burden and does meaningfully explain wallet_address, agent_wallet_id, and config_overrides. However, interval_seconds and caller_id receive no explanation, leaving two parameters with only type/default information as the basis for an agent's interpretation.

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 opening sentence states a specific verb and resource: 'Approve a StrategySuggestion, optionally creating the suggested Strategy.' It distinguishes this approval-and-create path from a manual 'suggested_config' round-trip through strategy create tools, so it is clear which operation is uniquely performed here.

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 explicitly positions this as the 'MCP-only closing move for get_strategy_suggestions' and instructs agents to 'pair with backtest_strategy + get_risk_assessment first'. It also specifies when not to use the manual create-path alternative because that 'silently drops the suggestion linkage.'

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?