AlgoVault — Crypto Quant Trade Calls

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

Annotations already declare readOnlyHint=true and destructiveHint=false; description adds that it 'calls an LLM, no other side effects' and provides quota details. This goes beyond structured annotations by clarifying runtime behavior and consumption costs. No contradiction.

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

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

Three sentences, each with a distinct purpose: output definition, usage guidance with alternative, and side-effect/quota disclosure. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With two parameters, no output schema, and strong annotations, the description covers purpose, usage, side effects, and quota. It tells the agent exactly when to use it, what it returns, and that it's read-only – sufficient for invocation decisions.

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

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

Input schema has 100% description coverage, with 'question' and 'model' fully described. The tool description adds no parameter-specific information beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states it 'Returns a synthesized natural-language answer with citations, grounded in the AlgoVault knowledge bundle' – a specific verb, resource, and output. It distinguishes from sibling search_knowledge by noting LLM synthesis, and from other siblings by focusing on knowledge Q&A.

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

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

Explicitly says 'Use when you need an explanation, code pattern, or how-to' and contrasts with search_knowledge: 'for raw ranked snippets without LLM synthesis use search_knowledge (faster, no quota cost)'. This provides clear when-to-use and an explicit alternative.

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

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

Adds context beyond the annotations: 'Read-only, live exchange APIs' and 'Verified track record, on-chain verified merkle anchor' provide useful behavioral and trust information. Also explains the composite verdict methodology. No contradiction with the readOnlyHint or destructiveHint annotations.

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

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

The description is compact and front-loaded with the output categories, making the primary purpose immediately visible. It includes an alternative tool reference and trust indicators in a short space, though the phrasing is slightly run-on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with no output schema, the description explains the return elements (regime, confidence, strategy hint), the composite methodology, the target asset class, and a key alternative. It doesn't specify exact output formatting, but that is acceptable without an output schema.

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

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

Schema descriptions already cover all three parameters (coin, exchange, timeframe) with examples and defaults, so the baseline is 3. The description does not add further parameter-specific semantics, but the schema provides sufficient guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool returns the market regime (TRENDING_UP, TRENDING_DOWN, RANGING, VOLATILE) with confidence and a strategy hint for crypto perpetual futures. The specific verb 'Returns' and resource 'market regime' make the purpose unambiguous, and it explicitly distinguishes from get_equity_regime for US equities.

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

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

Provides an explicit alternative for US equities ('For a US equity use get_equity_regime') and defines the asset scope as crypto perpetual futures. While it doesn't contrast with sibling tools like get_trade_signal, the distinct purpose of classifying market regime is clear enough to guide selection.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable context: 'Read-only: reads live exchange APIs, no orders.' This confirms the safety profile and explains the data source. It also mentions 'Verified track record, on-chain verified merkle anchor,' adding credibility context beyond annotations. However, it does not mention potential errors, rate limits, or fallback behavior.

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

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

The description is three concise sentences: the first explains what the tool returns, the second gives scope and alternatives, and the third covers read-only nature and trustworthiness. Every sentence carries meaningful information with no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description does a good job of outlining the return content: 'BUY SELL HOLD trade call with confidence and market regime.' It also covers scope, alternatives, and safety. Minor gaps include not describing how parameters like exchange or timeframe affect the result, though the schema covers their defaults. Overall, it is sufficiently complete for an AI agent to understand and invoke the tool.

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

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

Schema description coverage is 100%, so the schema already documents all parameters well. The description adds minimal parameter-specific context beyond what the schema provides—only the general notion of 'composite verdict' and 'one asset only.' This aligns with the baseline of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Returns a composite verdict — BUY SELL HOLD trade call with confidence and market regime — for one crypto or tokenized-stock perpetual futures.' It also explicitly differentiates from siblings by saying 'One asset only; for a whole-market scan use scan_trade_calls, for US stocks use get_equity_call.' This distinguishes it from scan_trade_calls and get_equity_call.

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

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

The description gives explicit 'when to use' guidance: 'One asset only' restricts scope, and it names specific alternatives: 'for a whole-market scan use scan_trade_calls, for US stocks use get_equity_call.' This provides clear direction on when this tool is appropriate and which sibling tools to use instead.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable context: 'Read-only: reads live exchange APIs, no orders' and 'This tool is an alias of get_trade_call — same behavior, kept for backward compatibility.' It also mentions a verified track record, though this is more promotional than operational. 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.

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

The description is concise: three sentences, front-loaded with the core purpose, then alternatives and read-only/alias context. The sentence 'Verified track record, on-chain verified merkle anchor' adds minimal invocation value and could be considered peripheral, so it doesn't earn a perfect 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the modifier complexity (5 params, no output schema), the description covers single-asset scope, alternatives, read-only behavior, and alias semantics. It also partially explains the output (BUY SELL HOLD trade call with confidence and market regime). Minor gaps like error handling or rate limits remain, but overall it is strong.

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

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

Schema description coverage is 100%, with each parameter already documented (e.g., coin examples, exchange default, timeframe default, assetClass force engine, includeReasoning). The description does not add parameter-specific semantics beyond what the schema provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Returns a composite verdict — BUY SELL HOLD trade call with confidence and market regime — for one crypto or tokenized-stock perpetual futures.' It clearly states the single-asset scope, distinguishing it from siblings by explicitly pointing to 'scan_trade_calls' for whole-market scans and 'get_equity_call' for US stocks, plus noting it's an alias of 'get_trade_call'.

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

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

Explicit usage guidance is provided: 'One asset only; for a whole-market scan use scan_trade_calls, for US stocks use get_equity_call.' This directly tells the agent when to choose this tool versus alternatives, and the read-only note clarifies it is safe for informational calls.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe. The description adds behavioral context: results are ranked, cross-venue, with a composite verdict per pair, and mentions an on-chain verified merkle anchor, which is extra useful context beyond the annotations. It does not describe pagination or output format, but with annotations covering the safety profile, this is reasonably transparent.

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

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

The description is a single, information-dense sentence that front-loads the core purpose (ranked cross-venue funding arbitrage) and adds relevant context (composite verdict, sibling references, on-chain anchor). It is concise and structured, though the trailing marketing phrases ('Crypto quant AI trading signal') add slight noise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is relatively simple (2 optional params, no output schema) and the description covers purpose, scope, and references to related tools. It orients the agent on what to expect (ranked pairs, verdict) and that it is a read-only signal, which is adequate for selection and invocation. It could mention the output format, but lack of output schema reduces the burden.

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

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

Schema description coverage is 100% (both limit and minSpreadBps are described in the schema). The description adds no parameter-specific semantics beyond mentioning funding rate spreads, but since the schema already fully describes the parameters, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool scans cross-venue funding arbitrage across major crypto perpetual futures venues, computes funding rate spreads, and outputs a BUY SELL HOLD composite verdict per pair. It uses a specific verb ('scan') and resource ('funding arbitrage'), and is distinct from siblings like get_trade_call or get_market_regime.

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

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

The description mentions this is an 'AI trading signal' and points to alternatives via 'Trade call via get_trade_call, market regime via get_market_regime', providing directional guidance. It does not explicitly say when not to use this tool vs. alternatives, but the cross-references and clear scope imply usage context.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, lowering the bar. The description adds useful context beyond that: 'Read-only: reads live exchange APIs, places no orders.' This confirms the external API access (matching openWorldHint) and explicitly rules out order placement, enhancing transparency without contradicting the annotations.

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

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

The description is a compact three-sentence structure: primary purpose, usage guidance with alternative, and safety note. Every sentence earns its place — no filler, no redundancy. It front-loads the most critical information and keeps the rest minimal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (11 parameters, no output schema), the description covers the essential behavior: what it returns, its scope, its usage nuance, and safety. It doesn't explain every nuance (e.g., exact ranking algorithm or response shape), but the schema covers parameters and the description clarifies the breadth-vs-depth positioning. Slightly more detail on return structure would push it to 5, but it's adequately complete for an agent to select and invoke it correctly.

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

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

The input schema provides 100% description coverage across all 11 parameters, with detailed field descriptions, defaults, enums, and constraints. The description itself does not attempt to restate parameter details, which is acceptable; the schema already carries the semantic load. No additional parameter meaning is added in the description, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Returns ranked BUY SELL HOLD trade calls across the top crypto perpetual futures by open interest' — a specific verb, resource, and scope. It also differentiates from the sibling get_trade_call by positioning this as the breadth scan, making it immediately distinguishable.

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

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

Explicitly states when to use this tool and when not to: 'Use this for breadth; use get_trade_call for per-coin depth and reasoning.' This names the alternative and gives a clear decision rule, which is exactly what high-quality usage guidance should do.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context beyond annotations: 'Fast: BM25 lexical search, no LLM call, no quota cost.' This discloses performance characteristics and resource implications. It also reiterates 'Read-only, no side effects', reinforcing but not contradicting annotations.

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

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

The description is four sentences, each serving a distinct purpose: purpose, usage timing, performance, and alternative tool. It is front-loaded with what the tool does and avoids fluff. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a simple 2-parameter schema, comprehensive annotations (readOnly, openWorld, non-destructive), and a clear description covering purpose, usage, performance, and alternatives, the tool definition leaves no significant gaps. Although there is no output schema, the description's 'ranked snippets' conveys the return format sufficiently.

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

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

Schema coverage is 100% and both parameters (query, limit) are adequately described in the schema itself. The description does not add extra meaning beyond what the schema already conveys; it only mentions the query type indirectly ('answering a question'), which does not materially enhance parameter understanding. Baseline 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Returns') and resource ('ranked snippets from the AlgoVault knowledge bundle'), and clearly scopes the domain (MCP tools, response shapes, integration patterns, code examples). It also distinguishes itself from chat_knowledge by emphasizing 'ranked snippets' vs. synthesized answers, and from other siblings by focusing on knowledge lookup.

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

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

The description explicitly tells the agent when to use it: 'Call this BEFORE other tool calls to confirm parameter usage and avoid hallucinating tool shapes.' It also names the alternative for a different need: 'For a synthesized natural-language answer use chat_knowledge.' These are clear usage directives and exclusions.

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