Foresea Forecasting

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

No annotations provided, so the description carries full burden. It discloses the workflow: fetches price, gathers evidence, computes edge, returns recommendation. Missing details on potential side effects or rate limits, but adequate for an analysis 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?

Well-structured with front-loaded purpose, triggers, example, and alternative. Slightly verbose but every sentence adds value. Could be tightened without losing clarity.

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 13 parameters and no schema descriptions, the description is incomplete. It explains key parameters and output shape, but many parameters are undocumented. Output schema exists, so return values are covered.

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 0%, so the description must compensate. It explains platform, slug, and ticker via example, but omits 10 other parameters (skills, variant, question, etc.), leaving their meaning unclear.

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: analyzing a specific prediction market by URL, slug, or ticker, answering whether it's over/underpriced. It provides specific triggers and example input, distinguishing it from sibling tools.

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 call (user mentions specific market by URL/slug/ticker) and when not to use (use foresea_forecast for general probability questions). Names the alternative 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?

With no annotations, the description fully discloses critical behaviors: quotes include fetched_at and age_seconds for freshness checking, both venues rate-limit hard (so quotes may not be live), one bad ref fails only that entry while the rest succeed, and there is a 50-ref limit. These are exactly the behavioral traits an agent needs to know, well beyond any schema 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?

The description is a single focused paragraph that front-loads the purpose, then adds essential operational details (format, rate limits, error handling, limit) without redundancy. Every sentence contributes value, and the example output further clarifies behavior without adding 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?

Despite moderate complexity (batch processing, partial failures, rate limits, output shape), the description is complete: it explains input format, limits, failure semantics, freshness metadata, and gives an example output shape. The presence of an output schema is supplemented by the example, making the tool fully understandable without further investigation.

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 only lists 'refs' without any description (0% coverage). The description compensates fully by defining the ref format as 'platform:ident' with concrete examples (kalshi:KXFED-25JUN-H, polymarket:some-market-slug) and specifying the 50-ref limit. It turns an opaque array of strings into a well-understood 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 fetches current price/volume for several markets at once, with the verb 'Call this when' and specific scenarios. It explicitly contrasts with foresea_analyze_market, making its unique purpose unmistakable.

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?

It provides explicit guidance on when to use the tool ('a watchlist, a portfolio, "check on these 5 markets"') and when not to ('instead of calling foresea_analyze_market once per market'), directly naming the alternative. This is exemplary 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?

No annotations are provided, so the description carries the full burden. It discloses the two possible response states ('status: running' or full report), advises to call again if not done, and explains that the research may still be running server-side. It could mention error handling or retry behavior, but is quite transparent for a simple polling 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?

The description is efficient and front-loaded with the trigger condition. Every sentence earns its place: the trigger, the response behavior, the restriction against speculative calls, and an illustrative example. No filler or redundant 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?

For a tool with one parameter and an output schema, the description covers all necessary context: when to invoke, what to pass, how to interpret the result, and what to do if still running. The output schema handles detailed return structure, so the description is sufficiently 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 schema only defines client_run_key as a string with 0% description coverage, so the description must compensate. It explains the key must come from a prior foresea_analyze_market call and provides an example usage, adding crucial context beyond the raw 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 specifies the tool's purpose: to check the status of an asynchronous research run initiated by foresea_analyze_market after it timed out or errored. It also differentiates itself from siblings by focusing on polling/checking rather than initiating or analyzing.

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 foresea_analyze_market times out or errors with a client_run_key) and when not to use ('Do not call this speculatively'). It also instructs to only use keys from prior calls, leaving no ambiguity about the trigger 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?

With no annotations provided, the description carries the full burden for behavioral disclosure. It only describes the action but omits any side effects, permissions, rate limits, or whether the tool is read-only or mutating. For a multi-agent debate tool, it is unclear if it makes external calls, requires authentication, or has costs. The description fails to disclose these behavioral traits beyond the basic action.

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, front-loaded sentence that packs the action, roles, and purpose without any wasted words. It is concise and well-structured, prioritizing 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?

Given the tool's complexity (multi-agent debate) and the presence of 4 parameters with zero documentation, the description is incomplete. It does not explain parameter semantics, behavioral traits, or how the debate is structured. Although an output schema exists (covering return values), it does not compensate for the missing guidance on inputs and operational behavior. The description is insufficient for a tool with such nuanced inputs.

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 0%, meaning the description explains none of the parameters. It only references a 'forecasting question' which maps to the 'question' parameter, but this adds no meaning beyond the schema itself. It does not clarify 'market_probability', 'resolution_criteria', or 'platform' defaults (e.g., 'Market'), leaving agents without understanding of how to use these fields.

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 action ('Conduct an adversarial multi-agent debate') and its purpose ('cross-examine evidence and isolate blind spots'), with specific roles (Bull, Bear, Chief Risk Judge) that distinguish it from sibling tools like foresea_analyze_market or foresea_forecast. The verb+resource is 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?

The description implies usage for forecasting questions but does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or mention any sibling tools. It offers context about the target domain but lacks direct guidance on when to prefer it over other analysis or forecasting 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?

With no annotations, the description fully handles transparency. It explains the tool returns ranked markets with directions, implied odds, historical significance, and multi-model comparison. No negative behaviors mentioned, but acceptable for a read-like 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?

The description is concise, front-loaded with action triggers, and every sentence adds useful 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?

Given zero parameters and a detailed output description, the description is complete. Sibling tools are listed for context, and the description covers what the tool does and what it returns.

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, so the schema coverage is 100%. The description adds value by explaining what the tool returns, which is sufficient 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 the tool's purpose: providing top trading opportunities with directions and historical backing. It distinguishes from siblings by focusing on 'model-vs-market disagreement' and the 'edge board', and includes specific user triggers.

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 says 'Call this when the user wants...' and provides good trigger phrases. It implies usage context but does not explicitly state when not to use 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?

With no annotations provided, the description carries the full burden and adequately discloses the tool's behavior: it returns the trading active flag and operational hours/schedule. No side effects, permissions, or rate limits are mentioned, but for a simple read-only status check with zero parameters, this is sufficient. Slightly more detail (e.g., real-time vs. cached) would improve 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 a single, well-structured sentence that front-loads the action ('Call this to check') and immediately lists the specific outputs. Every word earns its place, with no fluff or repetition of the function name.

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 zero-parameter tool with an output schema present, the description fully covers the tool's purpose and what it returns. It is complete and correctly scoped, matching the low complexity of the operation. No additional context is necessary to invoke the tool 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 schema provides complete coverage. Per the rubric, a baseline of 4 is appropriate since no parameter explanation is needed. The description focuses on the output semantics, which is the right emphasis for a no-argument operation.

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

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

The description uses a specific verb ('check') and resource ('Kalshi exchange operational status'), and explicitly names what it returns ('trading active flag', 'operational hours/schedule'). This clearly distinguishes it from sibling tools like foresea_analyze_market or foresea_orderbook, which focus on market data rather than exchange-level status.

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 phrase 'Call this to check...' provides clear contextual guidance for when to use the tool. It does not explicitly mention alternatives or exclusions, but given the tool's unique focus on exchange status among siblings, the use case is unambiguous. A brief note about not using it for market-specific data would have earned a 5.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds that the feed is 'real-time' and 'unified' and lists contents, but offers no insight into ordering, caching, rate limits, error behavior, or how 'edge' is computed. This is minimal additional context beyond the tool's name and title.

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?

A single, front-loaded sentence immediately identifies the action and resource, then efficiently lists the feed's components. No words are wasted, and the structure is easy to scan. Every element 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?

For a tool with two optional parameters and an output schema, the description adequately explains what the feed contains, but it omits crucial context about parameter usage (especially 'min_edge') and any caveats about real-time data. The presence of many sibling tools raises the need for clearer operational context, which is partially satisfied by the output schema but not by the description.

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 schema description coverage is 0%, yet the description makes no mention of the 'limit' or 'min_edge' parameters. While 'limit' is intuitive and 'min_edge' hints at a threshold, the description does not clarify the semantics of 'edge' in this trading/feed context or explain how parameters affect results. The description offers no compensation for the schema's lack of parameter documentation.

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

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

The description uses a specific verb ('Fetch') and resource ('real-time unified Foresea Alpha & Agent Feed'), then details the feed's components (edge signals, agent trades & theses, leaderboard standings), which clearly differentiates it from siblings like foresea_market_leaderboard or foresea_edge_board. This exceeds a generic paraphrase and tells the agent exactly what the tool provides.

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 is given on when to use this tool versus siblings. There is no mention of alternatives, exclusions, or scenarios where another tool would be preferred. The description only states what the feed combines, leaving the agent to infer usage context from the tool name and sibling names.

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?

With no annotations, the description fully discloses the tool's behavior: it returns a calibrated YES/NO probability (or numeric/date range), rationale, news evidence, and optionally market analysis (model probability vs market). It also states it handles multiple question types. No hidden side effects 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 informative and well-structured, starting with when to call, then detailing output, an example, and supported question types. It is somewhat lengthy but front-loaded with the most critical information. A minor reduction in examples could improve conciseness.

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 (13 params, no annotations, but an output schema exists), the description covers the core use case and return format well. However, it leaves many parameters undocumented, which is a gap for an agent attempting to use the tool optimally. The output schema mitigates some completeness concerns.

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 0%, so the description must compensate. It explains only a few parameters (question, market_probability, market_url) and alludes to options/categories for multiple-choice, but 13 parameters exist (e.g., variant, description, question_type, resolution_criteria) with no explanation. The description does not add sufficient meaning beyond the schema for most 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 is for forecasting questions about probability, likelihood, or whether something will happen, with explicit trigger examples and a detailed return specification (calibrated probability, rationale, evidence). The verb 'forecast' matches the resource, and the scope is well-defined, though it does not explicitly differentiate from siblings.

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 triggers (e.g., 'Will X happen?', 'What are the chances of Y?') and advises passing market_probability/market_url for market edge analysis. However, it does not explicitly state when NOT to use this tool or compare it to sibling tools like foresea_analyze_market or foresea_scan_markets, which would strengthen 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?

No annotations are provided, so the description must disclose behavioral traits. It only states 'fetch,' implying a read operation, but it does not mention authentication requirements, rate limits, or potential side effects. The description is insufficient for a tool with no annotation coverage.

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, concise sentence (18 words) that front-loads the action and resource. It is not verbose, but it could be more structured to include parameter hints or usage notes. Still, it earns its place with 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 the tool has two parameters with no descriptions and no guidance on valid values, the description is incomplete for effective use. The presence of an output schema covers return format, but the description does not explain how to specify what data to fetch, leaving the agent under-informed.

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 0%, and the description does not add any meaning to the two parameters ('data_type' and 'event_ticker'). Although the description hints at sports data, it fails to explain what values the parameters accept or how they map to the data types. The description must compensate for the lack of schema descriptions but does not.

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 'fetch' and the resource 'real-time sports game statistics, play-by-play data, and live event feeds from Kalshi.' It distinguishes the tool from siblings by focusing on live data, which is not covered by other tools like foresea_forecast or foresea_price_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?

The description provides a clear context for when to use the tool (when needing real-time data), but it does not explicitly mention when not to use it or suggest alternatives. The agent must infer from sibling tool names, lacking 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates a read operation ('fetch'), which is appropriate. However, it does not clarify what 'top profitable' means, how rankings are determined, whether data is real-time, or if there are limitations (e.g., pagination, rate limits). The description is minimally adequate but lacks depth for a tool with no annotation safety net.

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, 14-word sentence that is efficient and front-loaded. It conveys the core action without unnecessary words. However, it could be slightly expanded to include parameter guidance without losing conciseness.

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, output schema exists), the description is partially complete. The output schema likely documents return values, so that omission is acceptable. However, the description lacks context about when this leaderboard is useful relative to siblings, and it does not explain the 'limit' parameter. The completeness is adequate for a straightforward fetch but not comprehensive.

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 0%, meaning the input schema provides no descriptions for the single parameter 'limit' (optional, default 20). The tool description does not mention or explain this parameter at all. It fails to add any meaning beyond the schema, leaving the agent to guess the parameter's purpose and behavior.

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 'the top profitable prediction market trader leaderboard and rankings from Polymarket.' This is a specific verb-resource combination that distinguishes it from sibling tools like foresea_analyze_market (analyzes individual markets) and foresea_scan_markets (searches markets). The purpose is unambiguous and well-differentiated.

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 is provided on when to use this tool versus alternatives, such as when to use foresea_scan_markets for market discovery or foresea_analyze_market for deep analysis. There are no prerequisites, exclusions, or context given. The description simply says 'Call this to fetch...' without any decision-making support.

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?

No annotations are provided, so the description must fully disclose behavior. It mentions 'list' and returns 'active categories, tags, and classification taxonomy', which implies a read-only, non-destructive operation. However, it does not disclose details like response structure, pagination, or whether the data is cached. Given the absence of annotations, this is a minimal disclosure – adequate but not rich.

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 of 14 words, front-loading the action ('Call this to list'). Every word is informative, with no redundancy. It could be slightly more concise by removing 'Call this to' (just 'List active categories...'), but it's still 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?

Given that the tool has no parameters, a basic output schema exists, and the tool is simple (a taxonomy list), the description is largely complete. It explains the purpose and the nature of the data (active categories, tags, taxonomy). A 5 would require mentioning that the output schema covers the structure, but the current description is sufficient for an agent to decide to invoke this 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?

The input schema has 0 parameters with 100% schema description coverage, so the description doesn't need to explain parameters. It adds value by explaining what the tool returns (categories, tags, taxonomy), which aids the agent in understanding the output context. A 4 reflects that the description is clear about the lack of parameters and the return scope.

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 action ('list') and the resource ('active categories, tags, and classification taxonomy across Polymarket prediction markets'). It is specific and distinct from siblings like foresea_scan_markets, which likely scans for specific markets, not taxonomy. A 5 would require explicit differentiation from siblings like foresea_polymarket_meta.

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 that this tool should be used to retrieve taxonomy data, but there is no explicit guidance on when to use it versus other tools (e.g., foresea_polymarket_meta for broader exchange metadata, or foresea_scan_markets for market-level scanning). It does not mention when not to use it, which keeps it at a baseline adequate level.

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?

With no annotations, the description must carry the full burden. It clearly indicates a calculation (non-destructive) but does not disclose any side effects, dependencies on live data, or limitations. The phrase 'Grade A/B' hints at filtering criteria but adds no behavior beyond the verb 'Calculate.' It is not misleading but lacks depth.

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, front-loaded sentence that efficiently conveys the core action and scope. While it lacks parameter details, it is appropriately concise with no redundancy or 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?

The description provides the primary purpose but omits necessary context for a portfolio optimization tool with three parameters and no annotations. It does not explain how the parameters interact, what an optimal allocation entails, or any constraints. Given the tool's complexity and the sparse schema, the description is insufficient for a new 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 description coverage is 0%, and the description provides no meaning for 'min_edge,' 'bankroll_usd,' or 'kelly_fraction.' The term 'Fractional Kelly' hints at kelly_fraction but does not explain any parameter. The description fails to compensate for the undocumented 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 states a specific verb ('Calculate') and a clear resource ('optimal mathematical Fractional Kelly capital allocations and position sizes') with scope ('across live Grade A/B prediction market opportunities'). It clearly distinguishes from sibling tools that focus on analysis, scanning, or data retrieval.

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?

Usage is implied by the phrase 'across live Grade A/B prediction market opportunities,' suggesting it is for active markets, but there is no explicit guidance on when to use this tool versus alternatives, no exclusions, and no mention of prerequisites or sequencing with other 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?

With no annotations provided, the description must carry the full load for behavioral disclosure. It describes the action ('fetch live bids and asks orderbook depth') but does not state side effects (none expected), authentication needs, rate limits, or data freshness guarantees. The term 'live' is ambiguous—it could imply real-time or just current snapshot.

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, well-structured sentence that immediately states the tool's purpose and key details. Every clause adds value, with no redundancy or fluff. The action verb ('fetch') is 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 low complexity (one parameter, no nested objects, with output schema), the description covers the essential inputs and outputs. It mentions both supported exchanges and the return type ('bids and asks orderbook depth'). The output schema is present but not described, which is acceptable as per rubric. Slightly penalized for missing behavioral details (e.g., live vs cached data).

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 0% (the parameter 'ticker_or_token' has no description in the schema), so the description must compensate. It explains that the parameter accepts a Kalshi market ticker or Polymarket YES-token ID and gives examples. However, it does not specify format requirements (e.g., case sensitivity, full naming conventions) beyond the examples, leaving some ambiguity.

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: to fetch live bids and asks orderbook depth. It specifies the resource (orderbook depth) and provides concrete examples of supported identifiers ('KXFED-25JUN-H' for Kalshi, Polymarket YES-token ID), making it unambiguous and distinct from sibling tools.

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 includes a call-to-action ('Call this to...') but provides no guidance on when to use this tool versus sibling tools like foresea_recent_trades or foresea_edge_board. No alternatives or exclusions are mentioned, which limits decision support.

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?

With no annotations, the description carries the burden of disclosure. It implies a read-only fetch operation by listing data types, but does not mention rate limits, authentication, pagination, or target-specific behavior.

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

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

One compact, front-loaded sentence communicates the tool's purpose and key options without unnecessary words or repetition.

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 output schema covers return structure, and the description covers the three targets, but missing parameter semantics for 'market_id' and lack of target-parameter interaction details leave the description incomplete for complex use cases.

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 0%, and the description only explains possible values for 'target'. The 'market_id' parameter is entirely undocumented, and defaults or required relationships are not mentioned, leaving agents without enough information for correct invocation.

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

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

The description uses a specific verb ('fetch') and resource ('Polymarket metadata') and enumerates concrete target types ('series', 'comments', 'sports'), making the tool's purpose immediately clear and distinguishable from sibling market-data tools.

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?

It clearly states when to call the tool ('to fetch Polymarket metadata') and describes the three target modes. It does not explicitly name alternatives or exclusions, but the context is clear enough for basic selection among 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?

No annotations are provided, so the description carries the burden. It states 'retrieve' which suggests a read operation, but does not disclose any behavioral details such as data range limits, pagination, rate limits, or authentication requirements. The description adds the concept of OHLC candlesticks, but lacks depth for a tool without annotation support.

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, well-structured sentence with no extraneous content. It is front-loaded 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?

Given the presence of an output schema and two parameters, the description is too brief. It does not explain the output format, the difference between the two parameters, or how this tool fits with historical data needs. With many sibling tools, more context would be beneficial.

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 0%, meaning the description does not document any parameters. The description mentions 'ticker_or_market' in examples but does not explain the 'series_ticker' parameter or clarify how the two parameters interact. With zero schema descriptions, the description fails to add sufficient 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 the tool retrieves historical price series or OHLC candlesticks for a market, with concrete examples (Kalshi ticker, Polymarket slug). This distinguishes it from real-time data tools like foresea_live_data, though not explicitly. The verb 'retrieve' and resource 'price history' are 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 implies use for historical data but provides no explicit guidance on when to prefer this over sibling tools like foresea_analyze_market or foresea_scan_markets. It does not exclude any use cases or mention prerequisites.

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?

With no annotations, the description carries the full burden. It discloses that it returns recent public trades with prices, sizes, and timestamps. However, it does not explain the meaning of 'recent' (time window), the behavior of the limit parameter, or the valid values for platform. The lack of enum definitions in the schema compounds this gap.

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 conveys the core purpose. It is front-loaded with the action. However, its brevity leads to missing parameter and usage context. It earns every word but could benefit from a second sentence on parameters.

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 3 parameters with no schema descriptions and no enum constraints, the description is insufficient to fully guide the agent. It omits parameter details, valid platform values, and the behavior of the 'limit' field. The existence of an output schema partially compensates, but the description remains incomplete.

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 description adds no information about the three parameters (limit, platform, ticker_or_token). With 0% schema description coverage, the agent must infer from parameter names alone. The description does not explain defaults, valid values, or how to use them for filtering.

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 action (fetch), the resource (recent public executed trades/trade tape), and the data types included (prices, sizes, timestamps). It also specifies the supported platforms (Kalshi or Polymarket), distinguishing it from sibling tools like order book or price 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?

The description provides no guidance on when to use this tool versus alternatives (e.g., when should the agent use foresea_orderbook instead?). There is no mention of prerequisites, context, or exclusions.

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?

No annotations are provided, so the description carries full burden. It describes the return format (model probability, market price, edge) and includes an example output, implying a read-only operation. However, it does not explicitly state non-destructiveness or any safety aspects.

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 purpose, trigger list, output description, and example. It is concise but could be slightly tighter by removing redundant wording.

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 and no annotations, the description provides adequate context for usage and output but lacks parameter documentation. The output schema exists but its content is unknown; the description covers the gist of the return fields.

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 0%. The description only mentions platform and min_edge in an example, leaving limit, query, and evidence_top_k unexplained. With low coverage, the description should add meaning for all parameters, but it does not.

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 finds mispriced or interesting markets, with specific trigger phrases and a distinction from evaluating a specific market. Names the sibling tool foresea_analyze_market as the alternative.

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 (user wants to find trading opportunities) and when not to (evaluating a specific market, directs to foresea_analyze_market). Provides example triggers and a sample invocation.

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?

No annotations are provided, so the description carries the full burden. It clearly describes the output metrics and structure, but does not mention any potential side effects, data source, or update frequency. Since the tool has no parameters and is read-only, the behavioral disclosure is good but not exhaustive.

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 provides usage conditions and trigger phrases, the second lists the outputs. It is compact, front-loaded, and every sentence is meaningful.

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 zero parameters, no required inputs, and an output schema exists, the description is complete. It clearly states the purpose, triggers, and return metrics without missing essential 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?

The tool has zero parameters, so the baseline is 4. The description adds value by explaining what the return values contain, which goes beyond the empty input 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 explicitly states the tool returns accuracy, Brier score, calibration (ECE), and skill-vs-market broken down by time horizon. It also provides specific trigger phrases, making the purpose very clear and distinguishing it from sibling tools.

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 starts with 'Call this when the user asks how reliable or accurate Foresea is' and lists concrete trigger examples like 'How good is Foresea?' and 'What's the track record?'. This gives explicit guidance on when to use this tool vs alternatives.

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