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

The description adds context that annotations alone do not provide: the tool starts one run of the Apify Actor 'congism/polymarket-kalshi-arb-finder' through the hosted gateway with your own APIFY_TOKEN, the run consumes your Apify account, and the dataset, plus run and dataset IDs for paging, is returned. Read-only and open-world behavior is already declared in annotations and is not contradicted. It omits run duration, cost, and the consequence of omitting Kalshi credentials, which limits the score.

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?

It is well structured, with When to use, Returns, and Behavior sections that are easy to scan. The opening line just repeats the title, and the PredictIt and Arb Scanner sentence is promotional rather than operational, so both could be trimmed. It is otherwise dense and front-loaded.

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

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

For an eight-parameter tool with no output schema, the description covers what is returned, how paging works, and the auth requirement for APIFY_TOKEN. It does not explain optional Kalshi authentication, runtime, or cost implications, leaving gaps for an agent deciding when and how to invoke the tool.

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

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

The schema description coverage is 100%, so every one of the eight parameters is already documented with defaults and examples. The description adds no guidance on setting minSpread, minSimilarity, or the Kalshi credentials, and therefore it does not go beyond the schema, consistent with the baseline.

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

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

The description names a concrete verb and resource: it scans Polymarket and Kalshi for matching binary markets and identifies YES/NO price discrepancies that guarantee risk-free profit. That is far more specific than the title alone, and among its sports-odds siblings it offers a clear purpose. A minor deduction for the sentence 'Now covers PredictIt too - see our Arb Scanner', which suggests this tool may cover PredictIt even though it does not, muddying scope.

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

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

It includes an explicit 'When to use' line that limits the tool to price gaps between matching Polymarket and Kalshi binary markets, and it points to the Arb Scanner as an alternative for PredictIt. It does not state when not to use the tool, or the conditions that favor the sibling scanners, so the coverage is incomplete.

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

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

Beyond the read-only and open-world annotations, the description explains that a run is started on the Apify Actor via the hosted MCP gateway using the caller's own APIFY_TOKEN and account. It also states that the operation only reads public web data and returns dataset rows plus run and dataset IDs for paging, which is useful operational context. It does not discuss rate limits or billing beyond the schema's maxCostUsd, so it falls short of the richest behavioral disclosure.

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 organized into clear 'When to use', 'Returns', and 'Behavior' sections, with the core purpose front-loaded. The opening line repeats the tool title and name, which is slightly redundant, but the remaining content is efficient and easy to scan.

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

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

Given a 15-parameter scraper with a very rich input schema and no output schema, the description covers the essential context: what data is returned, how runs are authenticated, and that dataset IDs support paging. It does not document the row-level output shape, but the schema already carries nearly all parameter semantics, so the remaining gap is minor.

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 all 15 parameters are already documented in detail, including mode-specific behavior and required combinations. The description only loosely restates that multi-season and multi-league runs are possible and does not add syntax or format meaning beyond the schema, making the baseline score 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 states a specific verb and resource: scraping Understat xG, shot, PPDA, and season aggregate data across the Big 5 and RFPL. It enumerates the data families (player/team aggregates, match xG, shot-level coordinates, career histories, fixtures), which clearly separates it from the sibling odds and player-prop 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 gives a clear 'When to use' trigger: xG, shot maps, PPDA, and player or team season stats in the covered leagues. It does not name explicit alternatives or when-not-to-use conditions, so the agent must infer that odds-related siblings cover betting lines instead.

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

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

Goes well beyond the annotations by disclosing that each call starts a run of the hosted Apify Actor through mcp.apify.com using the caller's own APIFY_TOKEN and Apify account, which implies billing and quota implications. It also describes the notice items for empty or altered results and notes the run can be paged via the returned run and dataset IDs.

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 labeled sections (When to use / Returns / Behavior / Docs) and the key capability is front-loaded. The opening restates the title and league list at some length, which is mild redundancy against an otherwise tight body.

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 14-parameter tool with no output schema, the description still explains the return shape (one dataset row per result plus run and dataset IDs for paging), authentication requirements, and the optional notice rows. Nothing an agent needs to invoke it correctly 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?

Schema description coverage is 100%, so all 14 parameters — including the tricky dateMode semantics, team code formats, and the 366-day range cap — are already documented in the schema. The description adds only a high-level summary ('Filter by team, date, or status') and the notice behavior, so the baseline of 3 applies.

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

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

States a specific verb and resource ('Get live scores, schedules, and game results from ESPN') and enumerates the covered leagues, including the specialized 'find the next game of any team' capability. An agent can tell this is a scores/schedules tool rather than the odds, props, or analytics tools in the sibling set.

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?

A dedicated 'When to use' block names the conditions (scores, schedules, final results, next game) and the leagues that trigger it. It stops short of naming the sibling odds/analytics tools or stating when NOT to use it, so the routing decision is clear but not fully disambiguated.

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?

Well beyond the annotations, it discloses that the call starts a run of the named Apify Actor through mcp.apify.com using the caller's own APIFY_TOKEN and Apify account, and that premium billing applies to horse-history records. The read-only statement largely restates readOnlyHint/destructiveHint, but the auth and cost context is genuinely additive.

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 a clear purpose sentence followed by labeled When-to-use / Returns / Behavior blocks, which is easy to scan. Some filler ("the official source for North American racing," "Ideal for handicappers and sports analytics") does not earn its place.

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

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

With 11 optional parameters and no output schema, the definition covers the missing return contract by describing dataset rows plus run/dataset IDs for paging. It is adequate for correct invocation, with only the optional contact/feedback fields left unexplained.

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

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

Schema description coverage is 100%, so the schema already carries all parameter meaning; the description only reinforces the date/track scoping and the "one row per result" grain. It says nothing about the three sp_* feedback parameters, which a reader must infer from the schema alone.

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 and resource — "Scrape US Thoroughbred horse racing data from Equibase.com" — and enumerates the extracted entities (horses, jockeys, trainers, odds, finish order, times, payouts). It is clearly distinguishable from sibling sports-odds tools by domain, though it never names a sibling to route against.

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?

An explicit "When to use" section scopes it to US Thoroughbred entries and results for a date and track, and the parenthetical dataMode note (results only for past races, late_changes for today) gives real selection context. It stops short of stating when not to use it or which alternative sibling tool to pick instead.

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

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

Annotations already declare read-only, non-destructive and open-world, so the safety bar is low; the description still adds substantial operational context: it spins up an Apify Actor run under the caller's APIFY_TOKEN and account, returns run/dataset IDs for paging, and notes that unknown league paths are answered with suggestions and never charged. The proxy/IP-rotation behavior is also surfaced in the schema, reinforcing cost/rate-limit awareness beyond the annotations.

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

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

Well front-loaded: purpose, then When to use, Returns, and Behavior sections make it skimmable. It is somewhat repetitive, restating the five brand names in both the title line and the body, but no sentence is 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?

There is no output schema, and the description compensates by describing the return payload (one row per game, all book prices, best price per outcome) and the run/dataset IDs for paging. For a 7-param, zero-required, nested-object tool, an agent has everything needed to call it and interpret results.

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

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

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining that the operator enum maps to distinct brands/jurisdictions whose prices can differ, and that 'all' markets is priced higher and can return 300–500 markets per game. That adds decision-relevant meaning (cost and output shape) beyond the field descriptions, though it repeats the brand list already implied by the enum.

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?

States a concrete verb+resource (fetch live odds for games) plus scope: 24 Kambi-powered books, one row per game with best price per outcome. It explicitly differentiates from what it is not (DraftKings/FanDuel, historical odds), so an agent can separate it from siblings like sports-odds-scraper without opening a schema.

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?

Has an explicit 'When to use' block naming the condition (current pre-match/live prices from Kambi books, book comparison, best-price search) and an explicit exclusion ('Not for DraftKings/FanDuel or historical odds'). It never names a sibling tool directly, but the inclusion/exclusion conditions are unambiguous.

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/openWorldHint/destructiveHint, but the description adds real context beyond them: it runs an Apify Actor through the hosted MCP gateway, consumes the caller's own APIFY_TOKEN and account, and returns dataset rows plus run/dataset IDs for paging. It also documents dedupe-driven idempotency behavior, consistent with idempotentHint=false. It stops short of mentioning cost/credit consumption or runtime, which is the remaining material gap for a run-launching 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 definition is well front-loaded: one-line summary, then explicit When to use / Returns / Behavior / Docs blocks. Sentences are dense but each carries information. The only mild redundancy is restating the title's book list at the start of the summary.

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 16-parameter, no-output-schema tool, the description covers the essentials an agent needs before calling: auth token, account ownership, read-only nature, and the shape of the return plus paging IDs. Minor tension remains between "Keyless, no login" and the stated APIFY_TOKEN requirement, and there is no guidance on cost or the deprecated 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 description coverage is 100%, so the schema already documents all 16 parameters in detail, including the four deprecated no-op ones. The description adds only marginal mapping ("Moneyline, spread and totals", "American or decimal") and mentions just two of the four supported odds formats. It never warns that books, eventUrls, concurrency and proxyConfiguration are inert, leaving that entirely to 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 states a specific resource and scope: sports betting odds from DraftKings, Pinnacle and Bovada, one row per game, with moneyline/spread/totals and best-price/arbitrage. An agent can tell what it gets. However, with seven sports-odds siblings (e.g. publicrecords--sports-odds-api, congism--polymarket-kalshi-arb-finder) the description never explains how this differs from them.

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?

There is an explicit "When to use" clause naming the books, markets and league types that select this tool, which is more than most definitions offer. It gives no when-not-to-use conditions and does not route to any alternative tool, so the agent must infer exclusions itself.

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 read-only/open-world, but the description adds what they cannot: the run executes the Apify Actor through mcp.apify.com using the caller's own APIFY_TOKEN and Apify account, the output is dataset rows plus run/dataset IDs for paging, and cost-sensitive options (onlyWithOdds skipping paid matches, the incremental key-value memory store) are explained. That is substantial context beyond structured fields.

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 labeled blocks (statement, When to use, Returns, Behavior) with the key facts front-loaded. The league/market enumeration in the first sentence is mildly promotional fluff, but the rest earns its space.

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 24-parameter tool with no output schema, the description covers what is returned (structured JSON, one row per result, plus run/dataset IDs), auth requirements, and cost/memory behavior. Only the sibling-routing decision is unaddressed, which is a small gap at this 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 description coverage is 100%, so the 24 parameters are already fully documented with defaults, enums, and clamping behavior; the description adds no parameter-level meaning beyond what the schema says. Baseline 3 applies because the schema carries the burden.

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?

States a specific verb-and-resource combination ('soccer odds, football betting odds', markets, bookmakers, history back to 2005) and the Actor it invokes. It is specific enough to separate from generic sports-odds siblings, but it never names an alternative tool the way a top-tier definition would.

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 'When to use' line gives concrete scenarios — odds history, opening/closing lines, results and match stats for backtesting or closing-line value. It stops short of exclusions (e.g. when to use the ESPN or Understat siblings instead), leaving sibling choice to the agent.

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, openWorld, non-destructive, and non-idempotent, so the bar is lower, and the description still adds real value: it discloses the Apify Actor behind it, that execution runs through mcp.apify.com with the caller's own APIFY_TOKEN and Apify account (a cost/quota consideration), and that each call starts a fresh run. It also explains that only public web data is read. Minor gap: no mention of runtime or run-failure behavior.

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

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

The prose is sectioned into When to use / Returns / Behavior / Docs, which front-loads the decision-relevant content. The opening sentence redundantly restates the tool title verbatim before adding new information, which is the only real waste; the rest is dense with specifics.

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 an eight-parameter, all-optional scraper with no output schema, the description covers what an agent needs: what data comes back (dataset rows as JSON plus run and dataset IDs for paging the full dataset), how to discover valid league values, how to supply out-of-list leagues, auth requirements, and safety profile. Nothing material 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?

Schema description coverage is 100%, so all eight parameters are already self-documenting, and the enumeration in the description ('filter by league or player name') maps directly onto leagues/playerNames. The description adds no syntax or format detail beyond the schema, so it lands at the baseline plus a small credit for reinforcing the primary filtering axes.

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 gives a specific verb and resource ('Extract real-time player prop lines from PrizePicks') and enumerates scope: 29 leagues, over/under lines, odds tiers, stat types, 51 fields per prop. It implicitly separates itself from the sibling odds/analytics tools by naming a distinct source (PrizePicks) and a distinct payload (player props), though it never names an alternative directly.

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?

There is an explicit 'When to use' clause tied to a clear condition: questions about player prop over/under lines on PrizePicks for a league, team, or player. The schema also steers the discovery path (listLeagues to enumerate live leagues, extraLeagues for seasonal events). It stops short of naming when NOT to use it or which sibling to pick instead.

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