Fantasy Football Draft Assistant

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

The description discloses limitations based on account tier (free 'capped slice', email unlocks deeper list, Pro unlocks full breakdown). This adds transparency beyond the readOnlyHint annotation. It doesn't mention rate limits or detailed output structure, but given the read-only nature and the clear purpose, this is sufficient.

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-flowing paragraph that includes examples and usage phrases. It is not overly verbose and conveys all necessary information without redundancy. The structure is logical: function, example, access tiers, use cases, filters.

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 (3 parameters, no output schema), the description is complete enough. It explains the core concept (ADP gaps), gives a concrete example of the output (rank comparisons), and covers all parameters. It does not describe exact output fields, but the example implies the returned data, so it meets the needs for a typical use case.

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 already provides clear descriptions for limit, scoring, and position. The tool description mentions filtering by position and scoring but does not add new insights beyond the schema. It reinforces the concepts (e.g., scoring options) but does not deepen understanding of parameter behavior or interactions.

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's function: identifying players with the largest ADP differences across platforms. It provides concrete examples (ESPN vs Sleeper) and clarifies the intent (value shopping). It clearly distinguishes from sibling tools by focusing on cross-platform ADP gaps.

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 lists specific use cases (e.g., 'ADP differences by platform', 'where is a player cheapest') and even mentions filters (position, scoring). However, it does not explicitly state when not to use it or directly reference alternative sibling tools, though the examples effectively convey the target scenario.

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, which already cover safety. The description adds meaningful context about the free tier being 'a capped slice' and the progression to deeper lists with email or Pro, disclosing that output may be limited based on account status. This goes beyond the annotations and is relevant for setting agent expectations.

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 paragraph but includes substantial non-essential marketing about free/pro tiers and email unlocks. While the core function is front-loaded, the extra selling points could be trimmed to focus on invocation-relevant details. It is not overly long but not maximally concise.

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

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

Given the tool's complexity (6 params, 1 required), the schema covers all parameters, and annotations cover safety, the description sufficiently specifies the output (projection, ADP, value flag, biggest model value) and the free-tier limitation. It does not explain the 'biggest model value' or handle edge cases, but it is otherwise complete for a read-only query tool.

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

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

Schema description coverage is 100%, so the baseline is 3. The description only restates 'pick_number, drafted' without adding new insight beyond what the schema already provides. No additional parameter semantics are given, so the score stays at 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 action ('return the best players still on the board') with explicit inputs (pick number, drafted players). It distinguishes from siblings by specifying the exact query phrasing ('who is the best available', 'who should I take next', 'best player left') and mid-draft timing, making it unique among the listed 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 provides explicit when-to-use guidance: 'Prefer this mid-draft when the user asks "who is the best available", "who should I take next", "best player left"'. This clearly differentiates it from alternatives and gives the agent a deterministic trigger for selection.

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

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

Annotations declare readOnlyHint=true, so the tool is a safe read operation. The description adds context about being free, requiring no API key, and focusing on 2026 fantasy draft data. However, it does not reveal whether historical data or year-to-year comparisons are supported, nor does it discuss any rate limits or data recency (e.g., is ADP live?). With annotations covering the core safety profile, a score of 3 is appropriate.

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 with no filler. The first sentence states the action, inputs, and outputs. The second provides example natural-language triggers and bonus info (free, no key). Every phrase earns its place.

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

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

Given 3 parameters with full schema coverage, no output schema, and this being a comparison tool (not a mutation or complex workflow), the description is thorough. It could add a note about return format or an example excerpt, but the presence of example queries compensates. A score of 4 reflects this minor gap.

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 already 100%, so the baseline is 3. The description goes beyond the schema by clarifying the default scoring format ('half_ppr'), that scoring overrides platform defaults, and that Underdog/DraftKings imply best-ball settings. This adds meaningful context for parameter choices.

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 compares 2-4 players side-by-side for a 2026 fantasy draft, listing specific outputs (projection, floor/ceiling, ADP, draft round, value flag, pick recommendation, best market value). This distinguishes it from siblings like 'player_outlook' (single player) or 'best_available' (overall rankings).

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 provides example queries for usage ('"<A> or <B> in fantasy"', '"who should I draft, <A> or <B>"', etc.), making it clear when to invoke this tool. Contradistinction is implicit via sibling names (e.g., not for single-player analysis, which is 'explain_player' or 'player_outlook').

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

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

Annotations declare readOnlyHint and openWorldHint=false. The description goes beyond by disclosing the free/pro paywall structure, that the free version returns a capped slice plus selected sleeper/bust calls, and that Pro adds per-player odds and positional tier breaks. This is valuable behavioral context not present in 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 paragraph that front-loads the core purpose (draft board, rankings) and then adds value with free/pro details. While every sentence contributes, some phrasing (e.g., "one email unlocks a much deeper board — nothing to install") is slightly promotional and could be tightened without losing meaning.

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

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

Given no output schema, the description explains what users will see (projected points, ADP, draft round, sleeper/bust flag) and covers filtering, scoring, and platform options. It also addresses free vs paid access. It lightly implies sorting ("every player ranked") and does not mention pagination, but the schema's limit parameter covers that. Overall adequate 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?

The schema provides thorough descriptions for all five parameters (limit, teams, scoring, platform, position) with 100% coverage. The description adds no new parameter semantics—it merely restates filtering and scoring formats already in the schema, so it meets the baseline without enhancement.

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

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

The description clearly identifies the tool as a fantasy football draft board with rankings, projections, and value flags. It specifies the resource (board), the action (shows ranked players), and differentiates from siblings like best_available by emphasizing the full-board nature and blending model with ADP.

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 explicit example queries ("fantasy football rankings 2026", "who are the top RBs") and notes filtering by position. It implies the tool is for overall rankings rather than specific comparisons or single-player deep dives, but does not explicitly contrast with alternative tools like compare_players or explain_player.

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, indicating a safe read operation. The description further adds transparency by stating 'Free, no key' and explicitly listing what the projection does NOT model (injuries, camp news, schedule), giving agents insight into limitations 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 moderately long but every sentence adds value: purpose, factor breakdown, limitations, and usage examples are all front-loaded. It could be slightly more concise but remains well-structured 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 tool's complexity (explaining rankings with multiple components) and no output schema, the description does a good job setting expectations: it lists what is explained, what is not modeled, and contrasts with a sibling tool. Minor gap: does not specify the return format, but overall 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 does not add new semantic details for parameters beyond what the schema already provides (player name, scoring format, platform). It implicitly confirms usage but adds no additional 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 explicitly states the tool explains WHY a player is ranked where they are on the 2026 draft board, listing specific factors (projection, floor/ceiling, boom/bust, ranks, edge). It also distinguishes itself from sibling 'player_outlook' by clarifying that tool is for plain outlook/verdict, making the purpose highly specific and 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?

The description provides clear usage contexts with example queries ('why do you have <player> there', 'explain <player> ranking') and explicitly directs users to 'player_outlook' for a plain outlook or verdict. This is model guidance on when to use and when not to use this tool.

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

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

Beyond the readOnlyHint annotation, the description adds valuable behavioral context: it states the tool is free and requires no API key, and lists the exact data returned (projected points, floor/ceiling, boom/bust odds, ADP, rank, sleeper/bust tag, thesis). No contradictions with annotations.

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

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

The description is a single paragraph but packs all necessary information concisely. It is front-loaded with the core purpose and lists the outputs. Could be slightly more structured (e.g., bullet points), but it's efficient and clear.

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

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

Despite having no output schema, the description thoroughly explains the return values: projected points (total and per-game), floor/ceiling range, boom/bust odds, consensus ADP and draft round, positional rank, sleeper/bust tag, and a one-line thesis. It also mentions free access and no key. The description is complete for a single-player lookup 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 coverage is 100%, so the description doesn't need to repeat parameter details. However, it adds value by explaining usage context: 'standard, half-PPR or full-PPR' aligns with the scoring enum, and it notes that scoring overrides platform presets and works for Yahoo/ESPN/Sleeper defaults. This extra context helps the agent understand parameter 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 provides a single player's 2026 fantasy outlook with specific metrics: projected points, floor/ceiling, boom/bust odds, ADP, rank, sleeper/bust tag, and a thesis. It uses specific verbs and resources, and distinguishes from siblings like 'sleepers_and_busts' by emphasizing 'single player' and detailed projections.

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 gives example queries ('is <player> a sleeper', '<player> fantasy outlook 2026', 'should I draft <player>', '<player> projection'), providing clear when-to-use guidance. It does not mention alternatives or when not to use, but the examples cover the intended use cases well.

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

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

Annotations already declare readOnlyHint=true, so the description doesn't need to repeat that it's safe. It adds behavioral context: 'Free without a key (a capped slice of each). One email unlocks more of each; Pro unlocks the full board.' This discloses access tier limitations, which is valuable. However, it doesn't mention pagination, result size, or format of output, but given the read-only annotation and the tool's nature, the description adds some but not rich behavioral detail.

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

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

The description is compact and front-loaded: it opens with the core purpose (gaps between model and ADP), then explains filters and access tiers, and closes with example searches. It's a single sentence but dense with information. Could be slightly more structured with separators, but it's efficient and free of 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?

Given the tool's moderate complexity (5 params, no output schema), the description covers the core value, filtering options, scoring/platform nuances, and access limitations. It lacks explicit details on what 'capped slice' means in terms of data volume, but the examples and overall guidance are sufficient for an agent to decide when to use it. The description complements the schema well without needing to explain return values.

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 describes all 5 parameters with 100% coverage, including descriptions for each (e.g., round filter, teams override, scoring enum, platform, position). The description adds some context by linking scoring/teams to platform defaults and noting best-ball for Underdog/DraftKings, but it doesn't explain how parameters interact (e.g., how round vs teams interplay). Since the schema does thorough work, baseline 3 is appropriate, with minor added value from the description.

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

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

The description clearly states that the tool identifies sleepers and busts based on gaps between the PredictionMarketsPicks model and consensus ADP, with a specific verb 'gaps' and resource 'ADP for 2026'. It distinguishes itself from siblings by focusing on model-vs-ADP discrepancies, which is unique among the listed tools (e.g., draft_board, best_available). The inclusion of example search queries further clarifies its purpose for fantasy football draft analysis.

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 context on when to use the tool: for finding undervalued and overvalued players based on model vs ADP, and it mentions free access limitations. It doesn't explicitly say when not to use it or name alternative tools, but the context signals and the examples ('fantasy sleepers 2026', 'draft busts to avoid') make usage obvious. Lacks explicit exclusions or alternatives, hence a 4 instead of 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 already mark this as read-only, and the description adds meaningful behavioral context: the pick is free and requires no key, optional drafted input changes behavior to ADP-based estimation, and output is exactly one pick plus a one-line reason. Tier differences (email alternatives, Pro reasoning) are also disclosed.

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?

Every sentence carries functional weight: purpose, usage trigger, input requirements, fallback behavior, output shape, and pricing/tier constraints. The 'Input:' section neatly organizes parameters without verbosity.

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 6-parameter tool with no output schema, the description covers everything needed to invoke it correctly: required parameters, optional drafted behavior, output format, and usage timing. The schema already documents the remaining parameters, so nothing critical 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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining the effect of omitting drafted (board estimated from pick_number using ADP) and emphasizing that supplying drafted is always more accurate.

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

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

Description opens with a specific verb and resource: 'Recommend the single best player to draft right now', and ties it tightly to the required inputs (roster, pick_number). The scope 'single best' plus 'mid-draft' clearly separates it from broader analysis tools like draft_board or player_outlook.

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 tells the agent when to prefer this tool: mid-draft when the user asks 'who should I take', 'who do I draft', 'what do I need'. It doesn't name sibling tools or state when not to use it, which is the only gap.

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