fantasy-draft

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

Annotations include readOnlyHint=true, indicating a safe read operation, and the description adds meaningful behavioral context beyond that: free tier returns only top 5, a free key unlocks top 25, and Pro unlocks full per-platform breakdown. This discloses access limitations and result scope, which is valuable for the agent. 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 multi-sentence and slightly verbose, but each part serves a purpose: core function, example with concrete numbers, pricing tiers, explicit usage phrases, and filter option. It is front-loaded with the main purpose and remains readable without unnecessary 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?

Given the tool's moderate complexity (3 optional parameters, no output schema), the description covers the essential context: what it does, when to use it, example scenarios, and access restrictions. It does not describe return structure, but for a simple read-only list tool, this is acceptable and the overall guidance is sufficient.

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

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

The input schema has 100% description coverage, with each parameter (limit, scoring, position) already well-documented. The description only restates 'Filter by position' and does not add additional semantic detail, syntax, or relationships beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description uses a specific verb ('Find') and clearly identifies the resource: 2026 fantasy players with platform-specific ADP gaps (consensus vs ESPN, Sleeper, etc.). It distinguishes itself from siblings like compare_players and draft_board by focusing on cross-platform ADP arbitrage, and includes example queries that reinforce the unique purpose.

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 an explicit 'Use for' list with concrete search phrases ('ADP differences by platform', 'where is a player cheapest', 'ADP arbitrage'). It does not name alternatives or state when not to use the tool, but the examples and filtering options offer practical guidance for 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?

The description adds valuable behavioral context beyond the readOnlyHint: access tier limitations (free top 3, free key top 10, Pro full list) and the inclusion of the biggest model value. It does not cover error handling or response structure in detail, but for a read-only tool the core behavior is clear.

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 paragraph that covers purpose, access tiers, usage triggers, and inputs without unnecessary verbosity. Every sentence contributes meaning.

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

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

For a read-only tool with no output schema, the description adequately explains core behavior, input requirements, and access constraints. It could mention edge cases like exhaustion of players, but overall it is comprehensive enough for an agent 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?

All six parameters are fully described in the input schema (coverage 100%). The tool description only repeats 'pick_number, drafted' without adding new semantics, so it neither helps nor hurts beyond the schema baseline.

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

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

The description clearly states the tool's function: given pick number and drafted players, return the best available players with projection, ADP, and a value flag. It also specifies the exact use case ('who is the best available') and distinguishes it from general draft tools by emphasizing the mid-draft context.

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

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

The description explicitly says 'Prefer this mid-draft when the user asks...' and lists trigger phrases, providing unmistakable when-to-use guidance. It also implies the necessary inputs (pick_number, drafted), making usage conditions 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 already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds context beyond that: it's 'Free, no key', and it discloses that the output includes a pick recommendation and best market value. It also notes the draft year (2026) and scoring options, enriching the behavior without contradicting annotations.

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

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

The description is front-loaded with the core functionality in the first sentence, then adds 'Free, no key' and example queries. Every sentence contributes something: the examples are practical for agent trigger recognition. It is a bit longer than needed, but not wasteful, so it earns a 4.

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, so the description must convey the return content, which it does by listing the projection, floor/ceiling, ADP, draft round, value flag, pick recommendation, and best market value. It also covers unique usage contexts via example queries. Minor gaps like player-not-found behavior are not addressed, but for a read-only tool with good annotations, this is reasonably complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description mentions scoring formats ('standard, half-PPR or full-PPR') which aligns with the schema enum but does not add new parameter-level detail. It does map 'full-PPR' to the schema's 'ppr' value, which is slightly helpful, but overall the schema already explains the parameters adequately.

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 'Compare' and the resource '2–4 players side by side for a 2026 fantasy draft', and lists the specific outputs (projection, floor/ceiling, ADP, draft round, value flag, pick recommendation). This differentiates it from sibling tools like draft_board or best_available by focusing on head-to-head player comparison.

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 explicitly says 'Use for' and provides several example query formulations ('<A> or <B> in fantasy', 'who should I draft, <A> or <B>', etc.), which gives clear context on when to invoke this tool. It does not mention when NOT to use it or list alternative tools, so it misses the top tier for explicit 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?

With readOnlyHint=true in annotations, the description safely adds context about access tiers (free top 12, key top 50, Pro full board) and scoring formats. This goes beyond the annotations and gives useful behavioral detail about feature limits and prerequisites.

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 core purpose, then adds detail on features and access tiers. A few phrases are redundant with the schema (e.g., scoring formats), but overall it is organized and earns its length with value-adding details.

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 having no output schema, the description tells the agent what data will be returned (projected points, ADP, round, flags) and covers filtering options, access levels, and example use cases. For a read-only lookup with 5 parameters, this is 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 coverage is 100%, so the baseline is 3. The description mentions filtering by position and scoring variants, but the schema already describes each parameter adequately. The description adds little beyond what the schema provides, so no higher score is warranted.

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

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

The description clearly states it provides a fantasy football draft board with every player ranked, blending projections and ADP, and includes specific fields (projected points, ADP, draft round, value flags). It distinguishes itself from sibling tools by describing a comprehensive ranked board rather than niche analyses.

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

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

The description offers clear context on when to use it, listing example queries like 'fantasy football rankings 2026' and 'draft board'. However, it does not explicitly mention alternatives or when not to use it versus siblings, falling short of fully explicit when/when-not guidance.

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

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

Annotations already mark readOnlyHint=true, and the description adds operational detail that it is 'Free, no key' and lists the full set of returned data fields. It does not mention error handling for unknown players, which is a minor gap, but overall adds useful context beyond the annotations.

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

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

The description is a single, dense sentence that front-loads the core purpose and packs in the major output categories without obvious fluff. It concludes with concrete example queries, which is useful, though the sentence is long enough that it could be slightly more 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?

Since there is no output schema, the description correctly takes on the burden of explaining what the tool returns, covering projections, floor/ceiling, boom/bust odds, ADP, rank, and a thesis. It also notes that it is free and keyless, and gives example inputs, making it sufficiently complete for a tool of this moderate complexity.

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

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

The input schema already provides 100% coverage for all three parameters (player, scoring, platform) with clear descriptions and enums. The description's mention of scoring formats ('standard, half-PPR or full-PPR') merely echoes the schema's enum and adds no extra semantic meaning, 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?

The description clearly states it provides 'a single player's 2026 fantasy outlook' and enumerates specific outputs like projected points, floor/ceiling, ADP, positional rank, and a sleeper/bust tag. This distinguishes it from siblings such as compare_players or draft_board, which operate on multiple players or broader contexts.

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

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

The description gives explicit example use cases ('is <player> a sleeper', '<player> projection') that make the typical query context clear. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of the 'when/when-not' distinction required for 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?

Annotations declare readOnlyHint=true and openWorldHint=false, implying a safe, read-only, bounded query. The description adds valuable context: free tier limits (3 sleepers/3 busts), key-based upgrades (10 of each, Pro full board), and that platform defaults are overridable. It also clarifies the time period (2026) and scoring types. This goes beyond the annotations without contradicting them, though it doesn't mention rate limits or output format.

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 about 90 words, front-loaded with the core purpose ('biggest gaps...'), followed by filtering, access tiers, and use cases. Every sentence carries distinct information. It is efficient but slightly longer than necessary; still, each sentence earns its place, so it's not wordy.

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

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

With no output schema and only read-only annotations, the description must convey what the tool returns and how to interact. It does that: sleepers/busts, filters, access limits, and use cases. It could be more explicit about the exact return structure (e.g., whether results contain both categories or are separate), but given the simple list-style output and optional params, it is adequately complete for an agent to select and invoke the tool.

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

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

Schema description coverage is 100% for all 5 parameters, which all have descriptive text. The description only restates the existence of position/draft round filters and scoring formats, adding no new syntax or edge-case details. Therefore, baseline 3 applies; the description neither detracts nor adds meaningful semantics 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 defines the tool's purpose: returning the biggest gaps between the PredictionMarketsPicks model and consensus ADP, specifically labeled as SLEEPERS and BUSTS. It includes context like 2026, scoring formats, and filtering options, distinguishing it from sibling tools like adp_market_gaps or draft_board by naming a unique model and outcome (undervalued/overrated players).

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 lists use cases: 'Use for "fantasy sleepers 2026", "draft busts to avoid", "undervalued players", "overrated fantasy players", "late-round sleepers".' It also explains filtering by position/draft round. However, it does not explicitly provide negative guidance ('do not use when...') or name alternative tools for those cases, so it falls short of 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?

Discloses the free/Pro tier behavior (free pick, alternatives, full reasoning) and return format (one pick + one-line reason). This adds significant behavioral context beyond the readOnlyHint annotation, with 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, each carrying meaningful info. Front-loads purpose and usage. The input/output restatement is slightly redundant with schema but still useful for quick comprehension.

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

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

Covers purpose, input, output, and tier behavior. No output schema exists, so the description's statement of return format is valuable. Lacks edge-case details (e.g., empty roster, invalid pick) but overall complete enough 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 covers 100% of parameter descriptions. The description only restates the required inputs (roster, pick_number) without adding new semantics. Baseline of 3 applies; no extra value beyond 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?

States 'Recommend the single best player to draft right now' – specific verb, resource, and scope, including roster, pick number, and weighing need vs value. The usage hint about mid-draft further clarifies purpose. Though sibling alternatives are not named, the function's role is 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?

Explicitly says 'Prefer this mid-draft when the user asks...' and gives example phrasings. This provides clear when-to-use context but lacks exclusions or alternative tool mentions, so not a perfect 5.

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