kresmion

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

Annotations indicate read-only, idempotent, non-destructive behavior, which the description supports. The description adds useful context about the snapshot nature, default exchange, and that it provides descriptive market state, not advice. 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?

The description is concise, front-loaded with the purpose, and every sentence adds value. It is well-structured with a clear verb, resource, and additional context in two short paragraphs.

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 has an output schema (not shown) and annotations cover safety, the description is complete. It lists the key returned fields and explains the exchange parameter behavior. However, it could briefly mention that the output is a snapshot, not a historical series, to avoid ambiguity.

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 baseline is 3. The description does not add significant meaning beyond the schema: it mentions symbol set and exchange behavior, but those are already in the parameter descriptions. No additional clarification or examples are provided.

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 'Latest perpetual-derivatives snapshot' for crypto symbols, listing specific metrics (funding rate, open interest, etc.). It distinguishes from sibling tools by focusing on perpetual derivatives for BTC/ETH/SOL, while siblings like crypto_funding may be more specific.

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 when to use the tool: 'Reach for this to read positioning and leverage pressure (e.g. rich funding = crowded longs).' It also explains exchange behavior and defaults. However, it does not explicitly state when not to use it or mention alternatives like crypto_funding.

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, idempotentHint, destructiveHint. Description adds critical behavioral details: weekend rows forced to zero, low-confidence bars with flow_flag, and data source (SEC XBRL + yfinance). 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?

Front-loaded with purpose, then usage, then caveats. Every sentence adds value. No fluff. Well-structured for quick parsing.

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?

Has output schema, so return values are covered. Description provides source, caveats, and usage context. Siblings differentiate adequately. Complete for a read-only data 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%. Description does not add extra parameter details but contextualizes usage (look-back window, asset selection). The caveats indirectly enrich understanding of parameter effects.

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 'Spot crypto-ETF net flows: aggregate + per-product breakdown.' Identifies the resource (crypto-ETF flows) and action (net flows). Distinguishes from siblings like crypto_derivatives and crypto_funding.

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

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

Explicit context: 'Reach for this to see whether money is flowing into or out of the BTC / ETH / SOL spot ETFs.' Provides source and caveats. Does not explicitly list alternatives but context and sibling names imply differentiation.

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, idempotentHint=true, destructiveHint=false. The description adds context that funding is a positioning/leverage read, not advice, and mentions what each mode returns. However, it does not detail data frequency or update cadence, which would further enhance 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 compact and well-structured, front-loading the core purpose in a single sentence, then elaborating on the two modes with clear formatting. Every sentence adds value, and the whole is clearly scannable.

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 optional parameter, two clear output modes) and the presence of an output schema (not shown), the description fully covers the necessary context: what each mode returns, how to use it, and how it relates to siblings. No gaps remain.

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 documents the single parameter. The description re-iterates the parameter's two uses but adds no new semantic details beyond what is in 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 either the cross-exchange funding surface (latest funding per symbol across venues) or a single symbol's funding-rate history. It uses specific verbs like 'returns' and distinguishes itself from sibling tools (crypto_derivatives, crypto_liquidations).

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

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

The description explicitly instructs when to omit vs. provide the 'symbol' parameter and references alternative tools for related data (crypto_derivatives for perp snapshot, crypto_liquidations for liquidations). It also clarifies the interpretive nature of the data ('positioning / leverage read, descriptive only').

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 indicate read-only, idempotent, non-destructive behavior. Description adds critical context: data is single-venue (OKX), limited symbol set, and should be treated as a proxy. No contradiction with annotations; additional transparency on coverage and limitations.

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?

Description is concise, front-loading the main purpose, then providing details on usage, caveats, and metadata. 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 output schema exists and annotations are present, the description covers purpose, usage context, data limitations, and response metadata. It fully compensates for any missing structured information.

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 (hours and symbol) with descriptions. Description reinforces filtering by symbol and look-back window, and adds that omitting symbol returns all tracked symbols. Adds value 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?

Description clearly states the tool returns recent perpetual liquidations (forced deleveraging), split into long/short sides, with filtering by symbol and lookback window. It distinguishes itself from siblings like crypto_derivatives and crypto_funding by focusing specifically on liquidation 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?

Description implies usage for detecting liquidation cascades and capitulation events, and notes the data is a single-venue proxy. It does not explicitly state when to use this tool vs alternatives like crypto_derivatives or when not to use it, but the context is clear for its specific purpose.

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 read-only, idempotent, not destructive. Description adds critical behavioral caveat about BTC internal transfers dominating rows, which is key for correct usage.

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?

Well-structured: main sentence, then details, important caveat in caps, and alternative APIs. Each sentence earns its place; no fluff.

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?

Complete: covers purpose, parameters, caveats, alternatives, and return values despite output schema existing. Adequate for a complex tool with multiple 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 descriptions. Description adds context: explains min_usd as hard floor, direction values, blockchain options, and filter capabilities. Slightly above baseline due to reinforcing and adding nuance.

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 lists recent large on-chain transfers (whale/exchange flows, >= $100k). Distinguishes from sibling tools by specifying on-chain nature and caveats.

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 when to use (see notable on-chain movement) and when not to use (do NOT read BTC exchange netflow due to internal transfers). Provides alternatives for aggregate supply (stablecoins endpoint, unlocks).

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 idempotentHint; description adds beyond that: behavioral implications of long/short gamma, caveat that gamma is modeled/estimated, not actual positions. Adds significant context.

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?

Well-structured: summary line, then mode details, then behavioral implications, then caveat. No wasted words; each 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?

Output schema exists, schema coverage 100%. Description covers all necessary context: modes, interpretation, estimation warning. Fully complete for the tool's 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?

Schema already covers ticker with description; description adds detailed semantics: what each mode returns (net gamma, flip level, walls, etc.). Perfectly clarifies meaning.

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 returns modeled dealer gamma exposure, distinguishing between surface (no ticker) and detail (with ticker). Specific verb and resource, differentiates from sibling tools like equity_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?

Explicitly explains when to omit ticker for surface vs when to provide ticker for detail, with context on gamma interpretation. Lacks explicit alternatives but context is sufficient.

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, destructiveHint=false, idempotentHint=true. The description adds important behavioral context by clarifying that direction is an event tag, not advice, preventing misinterpretation. 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?

The description is concise (4 sentences), front-loaded with purpose, and well-structured. Every sentence adds value, 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?

Given the tool has 4 optional parameters and an output schema, the description sufficiently explains what the tool returns and how to filter. No gaps remain for an agent to use 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?

Schema coverage is 100%, so each parameter is already described. The description mentions filtering by signal_type, severity, and look-back window, which aligns with the schema but adds no new semantic 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?

The description clearly states the tool's purpose as 'cross-source equity signals from the Kresmion signal engine' and lists specific event types (SEC filings, insider trades, etc.). It distinguishes itself from sibling tools like equity_gamma by focusing on broad equity events.

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 tells when to use this tool: 'Reach for this to see recent notable equity events' and explains what it contains. However, it does not explicitly exclude alternatives or provide 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.

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

Annotations already mark the tool as readOnly and idempotent. The description adds behavioral details: sorting by market value, the qoq_signal, incomplete ticker resolution (~50-93%), and disclosure lags of up to 45 days, 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 concise (3 sentences) and well-structured: first sentence states purpose, second provides use case and ordering, third explains caveats. Every sentence earns its place 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?

Given the output schema exists and the tool is a straightforward read, the description covers all needed context: data content, ordering, filtering options, and important caveats (ticker nulls, disclosure lag). An agent can fully understand what to expect.

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 descriptions for all 4 parameters (limit, ticker, quarter, fund_cik). The description adds value by explaining how to use parameters effectively (filtering on cusip due to ticker issues) and clarifying defaults, going 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 returns SEC 13F-HR quarterly institutional holdings for tracked funds, specifying the source, frequency, and content (holdings, quarter-over-quarter changes, sorted by market value). This distinguishes it from sibling tools, which are crypto- or prediction-focused.

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 when to use the tool ('Reach for this to see what large funds hold') and provides caveats (ticker resolution incomplete, disclosure lag). However, it does not explicitly state when not to use or suggest alternatives, though no direct sibling exists.

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, idempotentHint=true, and destructiveHint=false. The description adds that each sub-section carries its own 'as_of' timestamp and states it is a descriptive, event-framed digest with no buy/sell advice. This goes beyond annotations by explaining output structure and nature.

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 relatively long but well-structured with sections and bullet points. It is front-loaded with 'START HERE' and the core purpose. While not the most concise, each sentence adds value and the structure aids 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?

For a complex digest tool with an output schema, the description thoroughly explains what is included for each asset class (crypto: derivatives, funding, liquidations, flows, prediction markets, macro; equity: signals, trades, holdings, gamma, prediction markets). It also notes that each sub-section has its own 'as_of' timestamp, preparing the user for the output format. No gaps.

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 the tool description adds significant meaning by explaining how 'symbol' is interpreted for crypto (BTC/ETH/SOL) vs equity (ticker like NVDA) and that 'asset_class' selects the product stack. This enriches 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 clearly identifies the tool as the flagship entry point that returns a full cross-product digest for a symbol. It distinguishes from sibling tools by explaining that it replaces stitching together multiple separate tools, listing specific product families covered for each asset class.

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

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

The description explicitly recommends starting here ('START HERE') and advises using family-specific tools only when more depth is needed ('Reach for the family-specific tools ... only when you need to drill deeper'). This provides clear when-to and when-not-to 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=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds behavioral context by specifying the per-family output structure (timestamp, row count, ok flag) and that each family reports independently. 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?

The description is concise (three sentences) and front-loaded with the core purpose. Lists families without excessive detail, every sentence adds value. No wasted words.

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

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

With zero parameters and an existing output schema, the description is complete. It explains the tool's purpose, when to use it, and what it returns. Provides sufficient context for an AI agent to select and invoke correctly.

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

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

The tool has zero parameters, so the description does not need to explain parameter semantics. According to the guidelines, 0 parameters gives a baseline of 4.

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 as a data-freshness health check across product families, listing families and return fields (timestamp, row count, ok flag). It distinguishes itself from sibling tools that provide specific data by acting as a meta-verification step.

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

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

The description explicitly tells when to use the tool: 'Reach for this FIRST to confirm the data behind an endpoint is fresh before you act on it.' While it doesn't list exclusions, the context is clear and provides actionable 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=false, destructiveHint=false, and idempotentHint=false. The description adds extensive behavioral context: creates a pending on-chain payment, requires user to manually send USDC externally, non-refundable, 30-minute expiry, only USDC on Solana mainnet, payment tied to API key, error handling with structured error dicts. 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 long but well-structured with clear headings (WHEN TO REACH FOR IT, THE FLOW, READ THIS BEFORE PAYING). Every sentence adds necessary detail for a payment tool. A minor reduction in verbosity could be possible, but the complexity justifies the length.

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 3 parameters, required action, and output schema, the description covers the complete workflow, all error states, prerequisites, and return types. It explains the full flow from plans to quote to payment to status polling, including timeouts and edge cases like underpayment or expiry. Very thorough.

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 adds significant meaning beyond the schema: explains action enum values with example contexts, shows plan key pattern 'boost_100k', tells where to get plan keys ('Get valid keys from action=\'plans\''), and describes payment_id origin ('Returned by action=\'quote\''). The parameter descriptions in the schema are also well-written.

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 buys monthly API quota with USDC on Solana. It distinguishes itself from all sibling tools by explicitly noting 'This is the ONE tool here that spends money. Every other tool is read-only.' The verb 'buy' and resource 'monthly API quota' are specific and 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?

Provides explicit when-to-use guidance: 'Use this after a 429 monthly-quota error.' Contrasts with per-minute 429 errors that need waiting. Clearly states alternatives: all other tools are read-only. Includes a full 4-step flow and pre-payment warnings.

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 idempotentHint=true. Description adds value by explaining the score scale, components, and that it's descriptive not a recommendation. No contradictions. Could mention rate limits, but not essential for read-only tool.

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?

Description is well-structured with front-loaded purpose, then return components, then usage guidance. Every sentence adds value, though slightly verbose with 'descriptive regime state, not a trade recommendation' which could be more 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?

Given zero parameters and presence of output schema, description fully covers purpose, return structure, usage context, and alternatives. No gaps.

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 0 parameters, so baseline is 4. Description does not need to add parameter info; schema coverage is 100%.

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 returns the current cross-asset Risk-On/Off macro regime with scores, sub-scores, z-scores, conviction, and interpretation. Verb 'Returns' and resource 'cross-asset macro regime' are specific. Distinguishes from siblings by mentioning alternatives.

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 'Reach for this for a one-call read of the market's macro backdrop.' Then provides clear alternatives for regime history and correlation breaks, telling the agent when not to use this 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?

The description adds significant behavioral context beyond annotations: it specifies that only contested markets (0.05 < YES < 0.95) are shown, introduces the 'contested_capital' weight, and warns that the date is the scheduled close, not the actual resolution time. No contradiction with annotations.

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

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

The description is well-structured with three distinct paragraphs: purpose, details, and caveat. It is concise without unnecessary fluff, but could be slightly more compact by merging the first two sentences.

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, output schema present), the description provides complete context: input meaning, output structure (grouped by date, contested_capital), and behavioral caveats. Nothing essential is missing.

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 single parameter 'days' already has a clear schema description ('Look-ahead window in days (max 60).'), so schema coverage is 100%. The tool description does not add meaningful new information about this parameter, 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 lists upcoming prediction-market closes across both Polymarket and Kalshi, grouped by date. It uses a specific verb ('list') and resource ('prediction-market closes'), distinguishing it from sibling tools like prediction_calibration or prediction_markets.

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 context on when to use the tool ('see what the crowd is about to be graded on') and includes a caveat about scheduled vs actual resolution. However, it does not explicitly state when not to use it or name alternative tools, missing some 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?

Discloses that returns Brier score, per-category Brier, and tail bias; annotations already indicate read-only and idempotent, and description adds context about what the data represents and constraints.

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?

Efficiently worded; provides essential information in a few sentences 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 zero parameters and an existing output schema, the description adequately covers purpose, interpretation, and limitations.

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%; description adds value by explaining the output and interpretation, meeting the baseline expectation.

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 historical calibration data for prediction crowds, including the Brier score and tail bias, which distinguishes it from sibling tools like prediction_markets and prediction_divergence.

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 to use this tool for judging how much weight to put on crowd probabilities in a given category, and notes it is historical only, not a forecast.

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 indicate read-only, idempotent, non-destructive behavior. The description adds rich behavioral detail: stale frozen leg exclusion, meta.stale_excluded reporting, the netting of executable_spread_pp against Polymarket execution cost, and the disclaimer that it is not an arbitrage signal. 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?

The description is well-structured with a clear front-loaded purpose and subsequent details in a readable format. It is slightly lengthy but each sentence adds necessary context, earning a high score.

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

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

Given the tool's complexity (2 parameters, single purpose), the description comprehensively explains what the tool returns, exclusions, optional parameter behavior, and caveats. The output schema covers return structure, making the definition 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?

The input schema has 100% coverage with descriptions for both parameters. The description adds significant value by explaining the meaning and limitations of executable_spread_pp (e.g., not floored at zero, only one leg considered) beyond the schema, enhancing parameter understanding.

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 explicitly states the tool 'returns linked Polymarket<->Kalshi pairs ranked by the absolute spread' between venues, clearly specifying the verb and resource. It distinguishes itself from sibling prediction tools by focusing on cross-venue divergence.

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 'Reach for this to spot where two crowds disagree on an identical question,' providing a clear use case. However, it lacks explicit guidance on when not to use it or alternatives among sibling tools, reducing the score.

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=true, idempotentHint=true, destructiveHint=false. The description adds substantial behavioral details: uses stored snapshots, never extrapolates beyond depth, gives median/p90 summary, and never places an order. 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?

The description is well-structured: a clear one-sentence summary, detailed functionality in the second paragraph, and caveats in the third. 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 presence of an output schema, the description adequately covers purpose, methodology, limitations, and what it does not do (no order placement, no extrapolation, market coverage). No gaps remain for an execution cost 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 baseline 3. The description enriches parameters by stating default values (100/1000/10000) and explaining that notionals are walked against one side. This adds meaningful context 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 verb 'model slippage/cost to FILL' and the resource 'given USDC sizes in one market'. It distinguishes itself from siblings like prediction_order_book by explicitly noting it uses stored snapshots and never places an order.

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 context on when to use the tool: to estimate execution cost and check tradeability. It includes caveats (one-leg, no fees, limited depth, market coverage) that imply limitations, but does not explicitly name alternative tools for live order books or round trips.

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, idempotentHint=true, destructiveHint=false. The description adds concrete return content (market row, outcomes, cross-venue comparison, 30-day delta) and notes the separate algo-flags endpoint, enriching 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 front-loaded with the main purpose and includes a secondary paragraph about algo-flags. While slightly verbose, every sentence adds value and it's 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 an output schema present, the description explains the key return elements and hints at additional functionality. It is complete for a detail-drilldown tool, though it could briefly note that the tool is read-only.

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 description for 'market_id'. The description adds value by specifying it's 'from prediction_markets rows', linking it to the parent tool's output.

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 specifies it returns 'full detail for ONE prediction market' including market row, outcomes, cross-venue comparison, and 30-day probability delta. It also distinguishes from sibling tools like 'prediction_markets' by stating 'Use it after prediction_markets to drill into a single question'.

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

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

Explicitly states when to use: after 'prediction_markets' to drill into a single question, or to compare same question across venues. It also mentions an alternative endpoint for algo-flags via the REST API or SDK.

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 idempotentHint. Description adds ordering ('oldest-first'), window direction ('most recent points'), and capping by limit. 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?

Five sentences, front-loaded with core purpose, no redundancy. 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?

With output schema present and full parameter coverage, description covers behavior (ordering, windowing), use cases, and constraints. Complete for a read-only data 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 100% with parameter descriptions. Description adds mutual exclusivity note for hours/days and clarifies window direction, which is value 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?

Clearly states it returns time series of YES probability and volume for one market, oldest-first. Distinguishes from siblings by focusing on historical data ('chart how a market's odds moved') and not a single snapshot.

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

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

Explicit when-use scenarios ('to chart odds movement' or 'detect repricing trend') and usage constraints (use either hours OR days, not both). No explicit sibling alternatives, but context is clear.

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=true, idempotentHint=true, destructiveHint=false. The description adds that only ACTIVE (unresolved, in-window) markets are returned, probabilities are crowd prices not forecasts, and what each row contains. 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?

Four sentences, front-loaded with the primary action and ordering. Every sentence adds value—no redundancy or fluff.

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 explains the output content (probability, change, volume, liquidity, etc.) and the restriction to active markets. With an output schema present, this level of detail is complete and 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 description coverage is 100% with detailed field descriptions. The tool description restates available filters (category, asset class, free-text, min volume) but adds little new semantic meaning. 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 specifies the verb 'search and filter', the resource 'LIVE prediction markets (Polymarket)', and the ordering 'volume-ranked'. It clearly distinguishes from sibling prediction tools by emphasizing 'live' and 'active unresolved' markets.

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 'Reach for this to see what the crowd is currently pricing on a topic' and contrasts with settled outcomes available through other tools. While it doesn't explicitly list when-not-to-use, the context is clear and implies 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, idempotentHint, and no destructiveness. The description adds that sports are excluded by default and explains the ranking metric (absolute probability move, gamma-native deltas), providing 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?

Three concise sentences. Front-loaded with main purpose, followed by usage guidance and parameter explanation. 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 the output schema exists, annotations are complete, and parameters are fully documented, the description covers all necessary context about usage, exclusions, and ranking logic.

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 adds useful context for the `include_sports` parameter (why default is false), but for others it mostly restates schema info, not adding significant meaning.

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 prediction markets with the biggest probability moves over 24h or 7d. It distinguishes from siblings by focusing on movers rather than calendar, calibration, or market details.

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 when to use: to find where the crowd changed its mind fastest. Notes sports are excluded by default with a clear reason, but does not explicitly list alternatives or cases when not to use.

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 readOnly, idempotent, non-destructive. Description adds valuable context: live with ~60s cache, as_of meaning, and emphasizes it never places an order.

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?

Efficiently structured: first sentence defines purpose, then returns, usage context, caching behavior, and alternatives. Every sentence earns its place with no fluff.

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 annotations covering safety, output schema present, and a single well-described parameter, the description is fully complete: covers what, when, how, and alternatives.

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 for market_id. The description adds no additional parameter details, but baseline is appropriate given high schema coverage.

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

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

The description clearly states it returns bid/ask depth, spread, and slippage-to-size for one market. It distinguishes itself from sibling tools by explicitly naming prediction_execution_cost for fill cost modeling and the REST API for history.

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

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

Provides explicit guidance: use to gauge market size absorption and fill cost before treating probability as tradeable; directs to prediction_execution_cost for specific USDC size and REST API for historical evolution.

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