PredMCP

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

The description explains the creation process and returns, and limits beyond the annotations. However, it does not disclose behavior on duplicate email or error conditions. Since annotations show readOnlyHint=false, no contradiction is present.

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 two sentences plus a third on limitations. Every sentence adds value, and the purpose is front-loaded. No redundant or filler content.

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 simple tool with one parameter and no output schema, the description covers input, output, and constraints. It could be improved by specifying idempotency or error handling, but it is largely complete for the given complexity.

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 covers the single parameter 'email' with a full description. The description adds a confirmation that email is required but does not add substantial new meaning beyond the schema. Baseline 3 applies due to 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 title and name clearly indicate creating an API key. The description specifies the action ('Generate a free PredMCP API key'), required input (email), and output (key and config). It is distinct from all sibling tools which are read-only or search operations.

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 states the requirement ('Requires an email') and usage limits ('Free tier: 100 calls/day, one key per IP'). While it does not explicitly contrast with alternatives, the context of sibling tools makes it clear this is the only creation tool.

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 (readOnlyHint, openWorldHint) already indicate safe read and external dependency. Description adds data source (Yahoo Finance) and feature split (Pro) but no additional behavioral traits like rate limits or freshness.

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?

Two front-loaded sentences, no wasted words. Efficiently lists indicators and features.

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 no parameters and no output schema, description covers purpose and data source adequately. Lacks output structure details, but acceptable for a simple snapshot 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?

No input parameters, so schema coverage is 100% by default. Baseline 4 applies; description does not need to add parameter detail.

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 clearly specifies the tool retrieves basic macro indicators (DXY, US10Y yield, S&P 500, gold, VIX) with raw values and 1-day change, differentiating from siblings like get_macro_context that imply broader scope.

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?

Implicitly suggests use for quick macro snapshot, but no explicit when-to-use or comparison with sibling tools like get_macro_context or get_macro_liquidity.

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 only provide readOnlyHint and openWorldHint. The description adds behavioral context: it involves orderbook calls (each top_n costs a call), computes net carry including costs, and provides additional metrics (break-even holding period, stability score). No contradictions detected.

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?

Two sentences, zero wasted words. Front-loaded with the core definition, followed by sibling differentiation. Every sentence serves a purpose.

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?

Despite no output schema, the description covers what is returned (net carry, break-even, stability score) and notes the cost of orderbook calls. For a tool with two parameters and good annotations, this is fully complete.

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 parameters have descriptions. The description adds value by explaining the cost implication of top_n ('each costs an orderbook call') and that size_usdc is used to compute costs. This goes beyond the schema descriptions.

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 states a specific verb ('get') and resource ('carry scanner'), and clearly defines what it computes: 'funding carry NET of costs: annualized funding minus (spread + 2x slippage at your size), with break-even holding period and a 7d funding-stability score'. It explicitly distinguishes from sibling 'get_top_funding_rates' which shows gross.

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 directly contrasts with a sibling: 'get_top_funding_rates shows gross — nobody trades gross.', implying this tool should be used for net carry analysis. While it doesn't list specific when-not-to-use scenarios, the context is clear enough for an agent to decide.

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 indicate readOnly and openWorld. Description adds that data comes from Etherscan free tier, implying potential rate limits and data freshness. No contradictions 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?

Three sentences with no fluff: first defines purpose, second explains interpretation, third notes data source. Highly efficient.

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 simple tool with two parameters, the description is mostly complete. However, it does not specify the return format (e.g., single number vs. time series), which could be helpful. Overall adequate.

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%, and the schema already provides good descriptions for both parameters. The description mentions 'over a window' but does not add significant new meaning beyond the schema.

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 it retrieves net ETH outflows across specific CEX hot wallets, with interpretation of outflows as bullish and inflows as distribution pressure. It distinguishes itself from sibling tools focused on derivatives, markets, or signals.

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 provides clear usage context (on-chain flow analysis) and interpretation of results. It does not explicitly state when not to use it or alternatives, but the purpose is well-defined and easy to understand.

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 openWorldHint=true. The description adds value by explaining the output ranges (-100 to +100 and 0-100) and the composite nature, which helps the agent understand what the tool returns beyond the safety 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 single sentence that packs key information: what it aggregates, output range, and efficiency. It is front-loaded and concise, but could be slightly restructured for readability.

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 no output schema, the description adequately specifies output format (directional and strength scores). With 3 parameters, all covered in schema, and low complexity, the description is complete enough for an agent to use 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?

Input schema has 100% description coverage, so the schema itself documents parameters well. The description doesn't detail parameters further, but coverage is high; baseline 3 is appropriate as the description adds limited meaning beyond the schema.

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 aggregates multiple signals (funding outlier, whale imbalance, OI/volume ratio, momentum) into a single directional score and a strength score. It uses specific verbs and resource, distinguishing it from sibling tools that focus on individual data.

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 implies usage for consolidated sentiment without multiple lookups. While it doesn't explicitly list alternatives or when-not-to-use, the 'one call replaces 6+ lookups' suggests efficiency, and sibling names provide context for granular alternatives.

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 and openWorldHint. The description adds context about data source (HL's predictedFundings feed) and sorting by annualized spread, but no additional behavioral traits like data availability or response structure.

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 progressively more specific: first defines data source, second explains the strategy, third states sorting. No redundant 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?

Covers data source, strategy, and sorting, but does not describe output format (columns, values) despite no output schema. Minor gap for a tool with two parameters.

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% with parameter descriptions. The tool description explains 'annualized spread' linking to min_spread_annual_pct, adding marginal value but not exceeding the baseline.

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 retrieves predicted funding spreads between three specific venues (Hyperliquid, Binance, Bybit) and explains the delta-neutral carry strategy, distinguishing it from sibling tools focused on single-venue funding rates.

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 implies use for cross-venue arbitrage opportunities but does not explicitly exclude alternatives like get_funding_rates or provide when-not-to-use guidance relative to siblings.

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 openWorldHint=true, so the description does not need to restate safety. It adds valuable context about the analysis methodology (comparing multiple timeframes, flagging anomalies) beyond what annotations provide. No contradictions.

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: core task, flags, and differentiation. Every sentence adds value without redundancy. Efficiently front-loaded with key information.

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 one parameter, no output schema, and readOnly annotations, the description sufficiently covers what the tool does and its outputs (flags). It could potentially detail the return format or interpretation hints, but for an anomaly detection tool it is adequately complete.

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% with the 'asset' parameter described as 'Asset ticker, e.g. "BTC", "HYPE"'. The tool description does not add additional meaning beyond the schema, so baseline score of 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 clearly states it performs term-structure analysis of Hyperliquid funding, comparing current vs 8h avg vs 24h avg vs 7d baseline, and flags spikes, regime shifts, sign contradictions. It distinguishes itself from the sibling get_funding_rates and similar tools by being 'more nuanced than raw funding rate', making its purpose unambiguous.

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?

Implies usage for detailed anomaly detection rather than raw rates ('More nuanced than raw funding rate'). However, it lacks explicit when-to-use or when-not-to-use guidance compared to the many sibling funding tools. The differentiation is clear but could be more direct.

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 openWorldHint=true. The description adds behavioral context by explaining the deviation calculation and that a spike vs. baseline is a stronger signal. No contradictions. It doesn't cover edge cases but adds value beyond 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?

Two sentences with zero wasted words. Front-loaded with the main action ('Hyperliquid perps whose current funding rate deviates significantly from their 7-day average'). Concise and well-structured.

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 no output schema, the description should explain return format; it only mentions 'perps' without structure or pagination. For a simple tool, it's adequate but incomplete. Complexity is low, so score 3.

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 covers both parameters with 100% description coverage (days and min_deviation_factor with defaults and ranges). The description mentions the 7-day average but does not add new semantic meaning beyond the schema. Baseline 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 returns Hyperliquid perps with funding rates deviating from their 7-day average, distinguishing it from siblings like get_funding_rates (raw rates) and get_top_funding_rates (top rates). It emphasizes that a spike vs. baseline is a stronger signal, clarifying its specific use case.

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 implies use for detecting outliers but does not explicitly state when to use this tool versus siblings (e.g., get_funding_rates, get_top_funding_rates). No when-not or alternative guidance is provided, leaving some ambiguity for 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 declare readOnlyHint and openWorldHint, indicating safe, unfiltered data. Description adds the interpretation of rate polarity (positive vs negative), providing behavioral context beyond annotations. No contradictions.

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?

Two sentences, no wasted words. First sentence states purpose, second provides interpretation. Efficiently front-loaded.

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 simple read tool with good annotations, the description covers purpose and meaning. However, lacking details on return format (e.g., fields, units) since no output schema. Still adequate for the complexity.

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% coverage for the single optional parameter 'coins', which is well described. Description does not add extra semantics, so baseline score of 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 clearly states the tool retrieves current funding rates for Hyperliquid perpetuals and explains the meaning of positive/negative rates. This distinguishes it from sibling tools like get_top_funding_rates or get_funding_outliers.

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?

Description implies use when current rates are needed, but does not explicitly state when not to use or mention alternatives. With many sibling tools (e.g., get_top_funding_rates, get_funding_outliers), guidance would be helpful.

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 indicate readOnlyHint and openWorldHint. The description adds that it flags spreads above a threshold and explains what a spread means, providing useful context beyond 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 two sentences, efficient, and front-loaded with the purpose. Every sentence adds value without 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?

Given the simple single-parameter schema and annotations, the description provides enough context. No output schema exists, but the purpose is clear. Could mention output format, but not critical.

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 baseline is 3. The description mentions 'spreads above threshold' but does not add meaning beyond the parameter's schema, which already has a detailed description.

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 finds the same underlying market on HIP-4 and Polymarket and flags spreads above a threshold. It is specific and distinguishes from sibling tools focused on other metrics or venues.

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 implies use for detecting arbitrage opportunities between HIP-4 and Polymarket. It does not explicitly state when not to use or name alternatives, but the context is clear enough.

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 indicate read-only and dynamic nature; description adds value by specifying the market type (sports, late-game, high certainty). It does not disclose any additional behavioral traits beyond what annotations provide, but the context is useful.

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?

Two sentences, no wasted words, front-loaded with key purpose. Every sentence earns its place.

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 annotations and schema, the description fully explains what the tool returns and its filtering criteria. No output schema is needed for this list-based 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?

Input schema coverage is 100% with clear parameter descriptions. The tool description does not add meaning beyond the schema, meeting the baseline but not exceeding it.

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 retrieves sports prediction markets on Polymarket that are closing soon with a high-certainty leading outcome, using specific verbs and resources. It distinguishes itself from siblings like get_markets_near_resolution by focusing on late-game positioning and high certainty.

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 implies use for finding near-certain, soon-closing sports markets, providing clear context. However, it does not explicitly state when not to use it or mention alternatives among the many sibling tools, leaving some ambiguity.

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. The description adds valuable context on computation and output interpretation (strength based on liquidity), exceeding what annotations alone provide.

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?

Two sentences, front-loaded with core function, no redundancy. Every sentence contributes meaning.

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 a single parameter and no output schema, the description adequately explains input and output interpretation. Minor gap: does not specify output format details.

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 the description does not add significant new meaning beyond the schema's 'Asset ticker to analyze'. 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 verb 'get' and specific resource 'liquidation clusters' for a Hyperliquid perp, and differs from sibling tools like get_orderbook or get_funding_rates.

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 implies usage for identifying liquidation concentration levels but does not explicitly state when to use this tool over alternatives or exclude other contexts.

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 and openWorldHint. The description adds valuable behavioral context: data sources (Yahoo Finance, CoinGecko) and that it provides a coarse regime classification. No contradictions 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?

Two sentences, front-loaded with 'Live macro snapshot,' and no extra words. Every sentence earns its place.

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 zero parameters and no output schema, the description provides a reasonable list of returned items. However, it does not specify the structure or format of the snapshot, but for a simple list tool this is sufficient.

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?

With zero parameters, baseline is 4 per rules. Description adds no parameter info but none is needed. Schema coverage is 100% for nonexistent parameters.

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 it provides a live macro snapshot of specific assets and a regime classification. The verb 'get' with specific resource details makes the purpose immediately clear and distinguishes from siblings like get_basic_macro.

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?

No guidance on when to use this tool versus alternatives such as get_basic_macro or get_market_context. The description lacks when-not-to-use instructions or references to sibling tools.

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?

The annotations already declare readOnlyHint and openWorldHint, and the description adds valuable behavioral context by detailing the data components (ETF flows and stablecoin mint/burn) and their interpretation. This goes beyond the annotations, but it does not disclose additional traits like update frequency or data latency. Still, it provides meaningful transparency.

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 extremely concise, consisting of only two sentences that fully convey the purpose, components, and a key insight. Every word is necessary, and there is no redundancy or fluff. It is front-loaded with the core function and immediately useful for an AI agent.

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?

Considering the absence of parameters and output schema, the description is largely complete: it explains the inputs (though none required) and the output's meaning. However, it could be enhanced by mentioning the output format (e.g., a single value or time series) or data latency, but for a simple gauge tool, it suffices.

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?

With zero parameters and 100% schema coverage (since no properties), the description adds value by explaining what the gauge measures and how to interpret results (net inflow = bullish). Baseline for 0 params is 4, and the description meets that by providing conceptual meaning without needing to detail parameter syntax.

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 identifies the tool as a fiat-to-crypto liquidity gauge, specifying the exact data sources (BTC and ETH spot ETF flows from Farside, USDT and USDC on-chain mint/burn from Etherscan) and the interpretation (net inflow is bullish for risk assets). This provides a specific and unique purpose that distinguishes it from sibling tools like get_basic_macro or get_macro_context.

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 does not explicitly state when to use this tool versus alternatives, nor does it provide conditions or exclusions. While the purpose is clear enough for an agent to infer context (e.g., for gauging liquidity conditions), there is no direct guidance on when not to use it or which sibling to prefer in specific scenarios.

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 indicate read-only and open-world behavior. Description adds useful specifics about data sources (Polymarket, HIP-4, Hyperliquid) and data types (price, funding, OI), without 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?

Two sentences, front-loaded with purpose, 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?

Covers the key scope and data sources, but lacks an explicit listing of output fields. However, 'snapshot' sufficiently implies a summary, and no output schema is provided.

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 has 100% coverage for the only parameter (query) with clear examples. Description adds no extra parameter details, but schema is sufficient.

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 it provides a unified intelligence snapshot combining Polymarket, HIP-4, and Hyperliquid data, distinguishing it from sibling tools that focus on individual data points.

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 'One call replaces 3+ separate lookups,' guiding use when a consolidated view is needed. Does not explicitly state when not to use, but context implies alternatives for granular needs.

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 (readOnlyHint, openWorldHint) already indicate a safe, open-ended query. The description adds valuable behavioral details: it combines BTC trend, realized vol, Deribit IV, funding breadth, and OI crowding, which goes beyond annotation information.

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?

Two sentences, both essential. Lists outputs in a clear, scannable format and provides usage guidance. 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?

Given no parameters and no output schema, the description sufficiently explains what the tool does and when to use it. Could optionally detail the return format, but not necessary for an agent to 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?

No parameters exist, so schema coverage is 100%. The description adds meaning by explaining the tool's output and purpose, which is more than baseline expectation for a parameterless tool.

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 it classifies market regimes with specific labels like RISK_ON_TRENDING. It uses a specific verb ('get') and resource ('market regime'), and distinguishes itself from siblings by being the first call each session.

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 instructs to call this tool 'FIRST each session to condition strategy choice,' providing clear usage context. Does not detail when not to use or compare directly with siblings, but context is strong.

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 indicate readOnlyHint=true and openWorldHint=true. Description adds that results are sorted by volume and lists specific return fields, providing useful behavioral context beyond 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?

Two sentences, no fluff, front-loaded with purpose and key details. Every word earns its place.

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 3 parameters, complete schema descriptions, and a description that lists return fields despite no output schema, the tool is reasonably complete for its complexity. Lacks usage guidance but otherwise sufficient.

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; all three parameters are well-documented. Tool description does not add significant new information about parameters beyond what the schema provides, so baseline 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 fetches live prediction markets from specific sources (Polymarket and/or HIP-4), sorts by volume, and lists returned fields (title, prices, volume, expiry). This differentiates it from siblings like search_markets or get_markets_near_resolution.

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?

No guidance on when to use this tool versus alternatives like search_markets or get_markets_near_resolution. Lacks explicit when-to-use or when-not-to-use 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 openWorldHint=true. Description adds context about filtering but no additional behavioral traits beyond what annotations provide.

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?

Two sentences, no wasted words. First sentence describes the tool, second sentence explains its utility.

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?

Good coverage given low complexity, schema handles parameters, annotations present. Minor omission: no indication of what happens with no results, but not critical.

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 baseline is 3. Description does not add meaning beyond the schema, as the schema already describes hours and min_prob with defaults and ranges.

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 it retrieves markets resolving soon with a probability threshold. Distinguishes from siblings like get_markets and get_late_game_sports by focusing on resolution time.

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 mentions usefulness for resolution arbitrage and last-minute positioning, providing context. However, it does not explicitly state when not to use it or compare to alternatives.

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 indicate read-only and open-world hints. The description adds that results are based on 24h volume spike or price swing and across specific platforms, but does not detail update frequency or other behavioral traits.

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 two sentences, front-loaded with the core purpose, and contains 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?

For a single-parameter tool with informative annotations, the description adequately explains what is returned and the scope. Missing output format details are partially mitigated by the lack of 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 coverage is 100% with a clear description of the limit parameter. The tool description adds no additional parameter semantics beyond what the schema provides, meeting the baseline.

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 it ranks top prediction markets by 24h volume spike or YES/NO price swing, surfacing breaking news bets and momentum plays. It specifies the scope (Polymarket and HIP-4) and distinguishes it from siblings like get_volume_spikes or get_funding_rates.

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 implies usage for finding trending markets and breaking news bets, but does not explicitly state when not to use it or mention alternative tools for related tasks.

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 openWorldHint=true. The description adds value by specifying the news sources (CoinDesk, The Block, etc.) and the pairing with 1h price moves, providing behavioral context beyond 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?

Two sentences, front-loaded with purpose, no wasted words. Efficiently conveys the core functionality.

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?

No output schema exists, so the description does not need to explain return values. The tool has low complexity with 2 parameters and no nested objects. The description provides sufficient context for usage, though it omits details like result format or pagination, which are not critical here.

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 has 100% description coverage, detailing both 'asset' and 'hours_back'. The description does not add significant meaning beyond the schema, as it only mentions the asset implicitly and does not elaborate on parameters. Baseline score of 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 clearly states the tool retrieves recent crypto news headlines for an asset paired with the subsequent 1-hour price move. It also mentions filtering news bias, which distinguishes it from the sibling tool 'get_recent_news' that likely returns only news without price correlation.

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 implies usage for analyzing how news affects price or filtering bias, but it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. The context is clear but lacks explicit guidance.

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 and openWorldHint, so safety profile is clear. Description adds context that it returns 'current' prices and implied probability, which is valuable behavioral information beyond annotations. No contradictions.

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?

Single sentence of 15 words, front-loaded with key action and resource. No wasted words; every part adds value.

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 simple two-parameter tool with no output schema, description adequately specifies what it returns (prices and probability) and the platforms it covers. Could mention dynamic nature more explicitly, but still complete for typical use.

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 for both parameters, clearly documenting platform enum and identifier types. Description does not add extra parameter meaning beyond what schema already provides, so baseline score 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?

Description uses specific verb 'get' and clearly identifies the resource ('YES/NO prices and implied probability') and scope ('any Polymarket or HIP-4 market token'). Clearly distinguishes from sibling tools like get_markets or get_orderbook.

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?

Implies usage when needing current odds from Polymarket or HIP-4, but provides no explicit guidance on when not to use it or alternatives among siblings. No exclusions or conditions stated.

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 openWorldHint=true. The description adds context about continuous snapshots and the unique data source ('Impossible without OI history... only predmcp records it'), which goes beyond annotations. No contradictions.

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, front-loaded with output and resource, then usage scope, then data uniqueness. No wasted words, effectively communicates key information.

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?

Missing output schema, and the description does not specify the exact structure of the response (e.g., single object or array, fields like coin, regime). While the regimes are listed, the format remains ambiguous. Adequate but not fully complete.

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 clear descriptions for both parameters. The description reinforces coin behavior ('scan all or one') but adds no extra semantic detail beyond what the schema provides. 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?

Clearly states the tool outputs 'Price-vs-OI regime per coin' with four specific regimes (NEW_LONGS, SHORT_SQUEEZE, NEW_SHORTS, LONG_LIQUIDATION), and distinguishes itself from siblings like get_oi_history and get_oi_near_cap by focusing on divergence classification.

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 implies the tool is for regime detection ('Scan all tracked coins or analyze one') but does not explicitly guide when to use it instead of other OI tools like get_oi_history for historical data or get_oi_near_cap for capacity analysis. No exclusions or alternatives are mentioned.

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?

The description does not contradict the readOnlyHint and openWorldHint annotations. It adds context about the data source (5-min collector) and the 24-hour lookback, which are useful behavioral details beyond 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 concise, with two sentences that efficiently convey purpose and context. It is front-loaded with the primary function and immediately adds value with the sibling tool reference.

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 description adequately explains the output includes price and funding at each point, and mentions the data cadence. Without an output schema, this is sufficient for an agent to understand the return structure.

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 the description does not add new meaning beyond the schema's parameter descriptions. The description mentions the 24-hour window, but this is already in the schema's max and default values.

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 provides an open-interest time series for a specific coin over the last 24 hours, including price and funding data. It distinguishes itself from the sibling tool get_oi_divergence, which classifies regimes.

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 explains the data is unique (not available on Hyperliquid) and offers an alternative tool for regime classification. It provides context for when to use this tool, though it lacks explicit when-not-to-use conditions.

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 indicate readOnlyHint=true, and the description adds behavioral context by explaining that new long positions cannot be opened on listed perps, which is beyond the annotation details.

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 two sentences: the first explains what the tool does, the second provides usage guidance. It is concise, front-loaded, and every sentence adds value.

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 no output schema, the description explains the tool's purpose and usage but does not specify output fields. However, for a simple list tool, the context is sufficient for selection and invocation.

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?

There are no parameters in the input schema, so the description carries no parameter info. However, it adds meaning about the output (lists perps at cap), which compensates for the lack of parameters.

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 lists Hyperliquid perps at the open interest cap, distinguishing it from sibling tools like get_open_interest and get_markets by focusing on those blocked for new long positions.

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 provides a clear use case: 'Use as a blacklist to avoid getting rejected on entry.' It implicitly tells when to use it (before opening longs), though it doesn't explicitly mention when not to use it or list alternatives.

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 and openWorldHint, so the description adds value by specifying it's a free Deribit feed and provides a snapshot. No contradictions 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 two sentences, concise, and front-loaded with key information. 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?

The description fully explains what the tool returns (list of metrics) and provides interpretive context. Since there is no output schema, this compensates well. The tool is simple with one param, so completeness is high.

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?

Only one parameter 'asset' with a clear enum and description in the schema. The description does not add additional meaning beyond the schema, resulting in a baseline score of 3.

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 retrieves a BTC or ETH options snapshot with specific metrics (ATM implied volatility, put-call skew, term structure, total OI, 24h volume). It distinguishes itself from sibling tools by focusing on options IV and Deribit feed.

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 explains the tool is useful as a sentiment gauge and provides interpretation (IV high = big moves; skew indicates hedging direction). It implies when to use it, though it does not explicitly mention when not to use or compare to alternatives.

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?

Description adds 'Shows liquidity at each price level' which is consistent with readOnlyHint and openWorldHint. But it does not provide any behavioral details beyond what annotations already indicate, such as the static nature of data or potential rate limits.

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?

Single, clear sentence that conveys the essential information without unnecessary words. Well-structured and easy to parse.

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 simplicity (one parameter, no output schema), the description adequately explains what the tool does and what to expect. It covers the orderbook depth and liquidity display. Could mention that it returns a list or snapshot, but sufficient for a simple 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?

Parameter token_id is fully described in the input schema. Description adds context that it is for any Polymarket market token and mentions bids+asks, which adds minor value. Schema coverage is 100%, so baseline 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?

Description clearly states the tool retrieves full orderbook depth (bids+asks) for a Polymarket market token, directly referencing the specific resource and action. It is distinct from all sibling tools, which are analytical or search-related.

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?

No explicit guidance on when to use this tool versus alternatives or when not to use it. However, given the sibling list, this is the only orderbook tool, so the usage context is implicitly clear but could be improved.

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 openWorldHint=true, indicating safety. The description adds behavioral details: returns 'top of book, spread, cumulative depth at $100/$500/$1k/$5k tiers, and estimated slippage,' and warns about slippage in low-liquidity assets. 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?

Two sentences front-load the purpose and return value, followed by usage context. Every sentence is informative and concise with no 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?

Despite no output schema, the description fully explains the return values (top of book, spread, cumulative depth at specific tiers, slippage estimate). Combined with clear purpose and usage context, the description is complete for a read-only query 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 coverage is 100%, so the schema already describes all three parameters (coin, side, size_usdc) with sufficient detail. The description only indirectly references the order size parameter ('for a given order size'), adding no new semantic information beyond the schema.

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 provides 'Full orderbook depth + slippage estimate for any Hyperliquid perp or HIP-4 market.' It specifies the resource (orderbook depth with slippage) and distinguishes itself from siblings like 'get_orderbook' by adding depth tiers and slippage estimation.

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 states it's 'Critical for HIP-4 farming and low-liquidity assets where market orders get destroyed by slippage,' providing clear context. However, it does not explicitly mention when not to use or name alternative tools, which would improve guidance.

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 and openWorldHint, so the description doesn't need to restate safety. It adds context about the signal's difficulty and provides an example, but doesn't detail pagination, rate limits, or result ordering.

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?

Two sentences, front-loaded with the core purpose, zero wasted words. Very concise and efficient.

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 simple tool with 2 parameters, good annotations, and no output schema, the description explains the concept and provides an example. It could mention the output format or ordering, but is largely sufficient.

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%, with both parameters (limit, min_pct) well-described in the schema. Description adds no extra meaning beyond what the schema provides, 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 clearly states the tool finds markets where PM implied probability diverges from HL funding direction, with a concrete example. It distinguishes from sibling tools like get_funding_outliers and get_hl_funding_pm_correlation by focusing on the divergence between specific metrics.

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 implies usage when interested in PM/HL divergences but provides no explicit guidance on when to use this tool versus alternatives like get_funding_outliers or get_hl_funding_pm_correlation. No when-not-to-use or alternative references.

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?

The description adds behavioral context by specifying it uses 14 days of 1-hour Hyperliquid candles. Annotations already indicate readOnlyHint=true, and the description aligns, providing data source detail without 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?

Two sentences: first lists outputs, second specifies data source. Both are concise and front-loaded with key information. No redundant 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?

Given one parameter, no output schema, and annotations present, the description covers what the tool calculates and its data source. It lacks explicit mention of return format, but the listed outputs implicitly convey structure.

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 for the single parameter 'positions' is 100%, so the description adds little beyond listing expected outputs. The description does not elaborate on parameter constraints beyond what the schema provides.

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 computes risk analytics for a list of positions, listing specific outputs like per-position beta, sector concentration, correlation matrix, volatility, and VaR. This differentiates it from sibling tools by focusing on portfolio-level risk metrics.

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 implies usage for portfolio risk analysis but does not explicitly state when to use this tool over alternatives. No mention of when not to use it or related tools.

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?

The description details the computation: fractional-Kelly, orderbook liquidity cap, ATR stop, liquidation price, funding carry cost, and risk percentage. It warns about liquidation inside stop. Annotations (readOnlyHint, openWorldHint) are consistent and the description adds behavioral context without 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?

The description is concise (3-4 sentences), front-loaded with the main purpose, and every sentence provides essential information without 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?

Despite no output schema, the description clearly enumerates what the tool returns (position size, stop, liquidation price, etc.) and mentions warnings. It is complete for the agent to understand the tool's behavior and outputs.

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?

With 100% schema coverage, all parameters are documented. The description goes beyond by explaining how they combine into the position calculation and mentioning warnings, adding significant semantic value.

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 purpose: converting a signal and bankroll into a concrete position with specific outputs like fractional-Kelly size, stop, liquidation price, etc. It distinguishes itself from sibling tools, which are mostly data retrieval, making it unique.

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 advises grounding win_rate_pct using get_signal_performance or get_signal_backtest, providing clear guidance on preparatory steps. Implicitly, it's used after having a signal, but no explicit when-not-to-use is given.

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 indicate readOnlyHint=true and openWorldHint=true. The description adds value by specifying the computation source ('30d of HL hourly candles') and listing exact metrics, providing transparency beyond the annotations. No contradictory behaviors are implied.

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: two sentences. The first efficiently lists key outputs, the second states data source. No extraneous information, perfectly front-loaded.

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 simple tool with one parameter and no output schema, the description fully enumerates the returned metrics (mark price, returns, high/low, etc.) and data source, making it complete for an agent to understand what the tool provides.

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% coverage with description 'Asset ticker, e.g. "BTC", "HYPE"'. The tool description itself does not add further semantics about the parameter; it only explains the output. Baseline of 3 is appropriate since schema already fully explains the parameter.

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 provides a 'one-call snapshot' with specific metrics (mark price, returns, high/low, drawdown, rally, volatility). This distinguishes it from siblings like get_market_context or get_orderbook by focusing solely on price summary metrics derived from 30 days of HL hourly candles.

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 implies usage for quick price stats ('one-call snapshot'), but does not explicitly list when to avoid or name alternative tools. The context from siblings (many specialized get_* tools) makes the scope clear, but lacks explicit when-not guidance.

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 indicate read-only and open-world behavior. The description adds valuable context: specific news sources and the Pro feature for price move data. No contradictions 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?

Two concise sentences covering core purpose and an optional Pro enhancement. No redundant information, efficiently front-loaded.

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?

Lacks explicit output structure description (e.g., fields returned). While schema covers inputs, the output is undefined. For a simple headline tool, this is a minor gap given no 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 coverage is 100%, and the description reinforces the 'asset' parameter purpose. It does not detail limit or hours_back beyond schema defaults, but that is acceptable given schema clarity.

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 it retrieves recent crypto news headlines for a specific asset ticker from named news sources (CoinDesk, The Block, etc.). It distinguishes itself from sibling tools like get_news_correlation by focusing on raw headlines.

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 implies usage for fetching headlines filtered by ticker, but does not explicitly state when to avoid this tool or provide alternatives. No direct sibling competition, so the guidance is adequate but not exhaustive.

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?

Beyond annotations (readOnlyHint, openWorldHint), description adds cursor-based pagination behavior, mentions next_cursor parameter usage, and explains the temporal scope (last hour). No contradictions.

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?

Two sentences that efficiently cover purpose, details, and comparison. Front-loaded with most important information. 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?

For a simple polling tool with no output schema, description adequately explains event types, pagination, and alternatives. Could mention return format briefly but not required.

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% with descriptions, but description adds valuable context: cursor mechanics (pass next_cursor as since_id) and free tier limit of 20 for limit parameter.

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 it retrieves server-detected events from the last hour, including specific types (funding outliers, whale trades, OI caps reached) with concrete thresholds. Distinguishes itself from siblings by mentioning polling equivalent and covering only recent data.

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 notes it is the polling equivalent of the /sse/signals stream and contrasts with get_signal_history which covers 7 days with outcomes, guiding when to use which.

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 indicate read-only and open-world. Description adds context on what the score reflects (spread, slippage, depth, etc.), providing insight beyond annotations. No contradictions.

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?

Two sentences, front-loaded with key information, every sentence adds value. 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?

Explains the score's meaning and composition. However, no output schema is provided and description does not hint at return format (e.g., numerical score, grade), which would be helpful for an agent.

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 covers all 3 parameters with descriptions (100% coverage). The tool description adds no additional meaning beyond the schema, so baseline score 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?

Clearly states it provides an execution-quality score for entering positions, listing specific factors and explicitly distinguishing from conviction (direction). Differentiates from sibling tool 'get_conviction_score'.

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?

Implies use when evaluating entry conditions and notes it is different from conviction, but does not explicitly state when not to use or name alternative tools for other purposes.

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, so the description adds little beyond stating it computes returns and Sharpe. It does not disclose potential side effects, rate limits, or data freshness. The openWorldHint is noted but not explained in the description.

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 sentences, front-loaded with the core action, followed by purpose and a promotional sentence. It is efficient but the last sentence is slightly self-congratulatory, reducing conciseness slightly.

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 no output schema, the description partially covers return values (forward returns, win rate, Sharpe) but does not specify data structure, pagination, or clustering behavior. It is adequate for basic understanding but incomplete for full agent decision-making.

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 has 100% description coverage for all parameters. The description summarizes the tool's action but does not add new details about individual parameters beyond what the schema provides. According to guidelines with high coverage, baseline 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's function: find historical signal instances and compute forward returns, win rate, and Sharpe. It specifies the resource (signal type on an asset) and differentiates from sibling tools like get_signals by focusing on backtesting and performance metrics.

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 does not provide explicit guidance on when to use this tool versus alternatives. It implies use for reasoning about expected value before trading, but lacks direct comparison to siblings or exclusionary 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 and openWorldHint. The description adds value by specifying the 7-day lookback, cursor-based nature, signal types included, and that forward returns are joined once mature. This provides behavioral context beyond 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 two sentences plus an example question, all front-loaded with key information: signal types, return horizons, time window, pagination, and use case. 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?

For a tool with 5 parameters, no output schema, and annotations, the description provides adequate context: what signals are returned, the time range, return windows, and cursor-based pagination. It misses explicit mention of the return format but the example compensates. Mostly complete.

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%, so baseline is 3. The description does not elaborate on parameter meanings beyond the schema's own descriptions (e.g., 'since_id' as cursor). It adds the context of cursor-based pagination but doesn't improve semantic understanding of individual parameters.

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 what the tool does: returns historical signal events (funding outliers, whale trades, OI caps) with forward returns, using cursor-based pagination. It also provides a motivating example question. This distinguishes it from siblings like get_recent_signals and get_signal_backtest.

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 implies usage via the example and mentions cursor-based pagination, but it does not explicitly state when to use this tool versus alternatives like get_recent_signals or get_signals. No direct comparison or when-not-to-use guidance is provided.

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 indicate readOnlyHint and openWorldHint, but the description adds behavioral context: data is from production signals (not backtest) and includes sample sizes for reliability judgment. This supplements the annotations well.

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?

Two sentences: the first states the core output and key differentiator, the second provides usage guidance and reliability qualifier. Every word adds value, no filler.

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 adequately explains the return values (hit rates and forward returns) and the reliability context. Could be slightly more detailed about output structure, but sufficient for agent usage.

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%, so parameters are fully described in the input schema. The description does not add further meaning beyond what the schema provides, meeting the baseline expectations.

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 it returns 'hit rates and average forward returns per signal type' and emphasizes it's based on actually-emitted production signals, distinguishing it from siblings like get_signal_backtest which are reconstructions.

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 recommends use for grounding win_rate inputs in get_position_size, and provides a caveat about sample sizes (n<10 as anecdotal). This gives clear when-to-use advice and a condition for reliability.

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 and openWorldHint, so the description's burden is lower. The description adds that the tool returns signals with reasoning, which is helpful context, but does not disclose additional behavioral traits like data freshness or rate limits.

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 two sentences long, directly states the core function, and includes an example. Every sentence adds value, and the structure is efficient and front-loaded.

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 moderate complexity, full schema coverage for the one parameter, and lack of output schema, the description adequately explains what the tool does and what it returns. It is complete enough for an agent to invoke correctly, though missing usage context.

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% for the single parameter 'coin', which has a description. The tool description does not add any further meaning or constraints beyond what the schema already provides, so a baseline score 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 detects divergence signals between Hyperliquid perpetual funding/OI sentiment and HIP-4 on-chain prediction market odds. It specifies the output includes BULLISH/BEARISH/DIVERGENCE signals with reasoning, providing a clear purpose that distinguishes it from generic tools, though not explicitly differentiating from similar siblings like get_pm_hl_divergences.

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 offers no guidance on when to use this tool versus alternatives such as get_hip4_vs_pm_arb or get_pm_hl_divergences. There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage independently.

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 openWorldHint=true. The description adds that the data comes from a free Deribit public feed and specifies the metrics (ATM IV, OI, volume), but does not disclose potential limitations like data freshness or rate limits.

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?

Two sentences with front-loaded key information. The first sentence clearly defines the tool's purpose, and the second adds the 'Pro' tier distinction. 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?

Given the simple tool with one parameter and annotations present, the description adequately covers what data is returned and hints at a more advanced version. However, it lacks details on return format or any usage caveats.

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 has 100% description coverage for the single parameter 'asset', including an enum of BTC/ETH. The tool description mentions these assets but adds no new meaning beyond what the schema provides.

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 it provides a snapshot of BTC or ETH options data (ATM IV, total OI, 24h volume) and distinguishes itself from the more comprehensive sibling 'get_options_iv' by being a simple, free Deribit feed.

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 implies usage for a basic free options snapshot, but does not explicitly state when to use this tool versus alternatives like 'get_options_iv'. No exclusion criteria or when-not guidance is provided.

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 indicate read-only and open-world behavior; the description adds context about output fields (OI, annualized yield) and ranking logic, which goes beyond 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?

Two sentences, front-loaded with purpose, followed by use case. No superfluous 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?

Provides enough context for a simple read-only tool with two optional params and no output schema; mention of OI and yield hints at return shape.

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?

Both parameters have descriptions in the schema (100% coverage). The tool description does not add additional parameter meaning beyond what the schema already provides.

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 ranks top perps by absolute funding rate, includes OI and annualized yield, distinguishing it from siblings like get_funding_rates and get_funding_outliers.

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 it is useful for finding overcrowded longs/shorts and carry opportunities, but does not mention when not to use or name alternative siblings.

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 declare readOnlyHint and openWorldHint, which are consistent with the description. The description adds that data sources are free (Tally + curated DB), providing useful behavioral context about cost and data origin.

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 two sentences: the first explains core functionality and examples, the second adds use case and data source. No redundant words, perfectly concise.

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 list tool without output schema, the description adequately tells what it returns (various catalyst types) and its purpose. It could note pagination or limits, but the provided info is sufficient for an agent to understand 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?

Both parameters (asset, horizon_hours) have descriptions in the input schema, so schema coverage is 100%. The description only echoes 'within a horizon' and does not add new meaning beyond what the schema already provides.

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 lists upcoming market catalysts for an asset within a horizon, specifying types like token unlocks, governance votes, ETF/SEC deadlines, and FOMC dates. This distinguishes it from sibling tools that focus on other data like funding rates, orderbooks, or signals.

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 says 'Helps agents avoid blind trades into known events,' which gives a clear use case. However, it does not explicitly mention when not to use or provide alternative tools, though the context implies checking catalysts before trading.

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 and openWorldHint. Description adds value by explaining the behavioral significance of volume spikes (preceding news events or informed positioning), which goes beyond the annotation cues. No contradictions.

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?

Two sentences, front-loaded with the core purpose. No redundant words. Efficient and clear.

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 simple list tool with self-explanatory parameters and no output schema, the description covers the main purpose and typical use. However, it omits details on output format or sorting, which would be helpful given the lack of 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 coverage is 100%, so the baseline is 3. The description does not elaborate on parameters (limit, min_ratio) beyond what the schema provides, so no additional value added.

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 identifies the tool as retrieving Polymarket markets with abnormal 24h volume relative to 7-day average, with a specific verb and resource. Distinguishes from siblings like get_movers or get_signals through the unique metric and use case hint.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies detection of news events or informed positioning but doesn't contrast with other market or signal tools. No when-not-to-use or alternative names provided.

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 and openWorldHint. Description adds valuable context: data source (durable trade tape, restart-proof), floor threshold ($25k), and persistence semantics. 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?

Two sentences with no filler. Front-loaded with key purpose and outputs. Every sentence adds essential information.

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?

Despite lack of output schema, description covers return values (imbalance ratio, verdict, largest prints). Parameters are fully described in schema. Could elaborate on 'largest recent prints' but sufficient for invocation.

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 baseline is 3. Description adds minimal extra meaning beyond param descriptions (e.g., 'top ~10 by OI' already in coin param description). No new insights on parameter usage.

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 clearly states the tool computes cumulative whale buy/sell imbalance over hours-to-days from durable trade tape, returning specific metrics. It distinguishes from sibling 'get_whale_trades' by noting longer horizons, making purpose unambiguous.

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?

Description explicitly contrasts with 'get_whale_trades' (longer horizons, 1h buffer), indicating when this tool is appropriate. However, it does not mention scenarios to avoid or list other alternatives, leaving some implicit guidance.

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 indicate readOnlyHint=true and openWorldHint=false. The description adds valuable context about the curated nature of the label DB (CEX, market makers, suspected funds), but does not specify behavior for unknown addresses (e.g., returns null/error). Overall, it supplements annotations well.

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 two sentences, front-loaded with the primary action and resource, followed by the purpose. No redundant information. Every sentence serves a clear purpose.

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 simple lookup tool with one parameter and no output schema, the description is complete. It explains what the tool does, why it's useful, and the nature of the data. No additional details are necessary for effective use.

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 has 100% coverage with a clear description of the 'address' parameter (0x-prefixed, 40 hex chars). The tool description adds context about label types but does not further clarify the parameter meaning beyond what the schema already provides. Baseline score of 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 clearly states the verb 'look up' and the resource 'Ethereum address against curated label DB', specifying the types of labels (CEX hot wallets, market makers, suspected funds). It distinguishes this tool from siblings like get_whale_positions or get_whale_trades by focusing on label 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 implies usage when an agent needs to distinguish mechanical MM flow from alpha-generating activity, providing context for when to use this tool. However, it does not explicitly state when not to use it or mention alternatives among the many sibling tools.

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 openWorldHint=true. The description adds context about the API limitation but does not mention rate limits, authentication needs, or response format. It does not contradict 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 two sentences, front-loaded with the main purpose, and includes a brief explanation of the required parameter. No extraneous 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?

For a simple read tool with three parameters and no output schema, the description covers the essential purpose and usage. It could mention pagination or response structure, but this is not critical given the tool's simplicity.

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. The description reinforces the user parameter usage but adds no additional semantic meaning beyond what the schema provides.

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 retrieves positions for a specific Polymarket wallet, optionally filtered to one market. It specifies the verb 'get', resource 'positions', and scope, distinguishing it from related tools like get_whale_flow and get_whale_label.

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 explains that the API requires a user address because there is no public 'all holders' endpoint, guiding the agent to pass a wallet address. However, it does not explicitly state when not to use this tool or mention alternatives among the siblings.

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?

The description adds context about the return fields and threshold behavior beyond the readOnlyHint annotation, but does not disclose additional traits such as how recent the data is, number of trades returned, or any pagination limits.

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, efficient sentence that front-loads the purpose and key content without any 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?

For a simple read-only fetch tool with no output schema, the description adequately explains what the tool returns, making it complete enough for an agent to understand the output.

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%, so the description's mention of 'notional threshold' adds minimal value over the schema's description of min_notional_usdc; 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 retrieves 'Recent large trades on Hyperliquid perps above a notional threshold' and lists the included fields (side, size, price, timestamp), providing a specific verb and resource that distinguishes it from siblings like get_whale_positions.

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 implies the tool is for fetching recent large trades but does not explicitly discuss when to use it over alternatives or mention any prerequisites, providing only implied usage guidance.

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 and openWorldHint; description adds that results are ranked and include current odds. No contradictions, and the description enriches understanding beyond 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?

Two concise sentences with no wasted words. All information is front-loaded and directly addresses the tool's purpose and output.

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 simple parameters, no output schema, and annotations covering safety and data freshness, the description is mostly complete. It could mention pagination or sorting details, but the provided 'ranked results' offers sufficient context for a search 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 coverage is 100% with detailed descriptions for both query and limit. The tool description adds no extra meaning beyond what the schema already provides, so baseline 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?

Clearly states 'Full-text search across all Polymarket and HIP-4 prediction markets' with a specific verb (search) and resource (markets), and distinguishes from siblings like get_markets which likely list all markets without search.

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?

Implies use for keyword-based search with 'Returns ranked results with current odds' but doesn't explicitly exclude alternatives (e.g., use get_markets for unfiltered listing). Provides clear context but no direct when-not-to-use guidance.

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