Server Quality Checklist

Tool Scores

• get_recordsA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It transparently states that it 'Supports natural language field names with fuzzy matching and variations', and that 'Additional match details may be included depending on the field', revealing behavioral nuances. It also clarifies the scope as 'the absolute highest values ever recorded in tracked matches'. However, it does not explicitly state that the operation is read-only or safe, which a fully transparent description would include.

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

  Conciseness4/5

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

  The description is long but well-structured: it front-loads the purpose, then gives usage examples, parameter details, return format, common queries, and a full example. Every section adds value, though it could be slightly more concise. The example output is helpful but not essential.

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

  Completeness4/5

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

  The description is highly complete for a single-parameter lookup tool: it thoroughly explains the parameter, describes the return object with field names and types, and provides a realistic example. It does not cover error cases (e.g., unknown field) or specify a limit on the number of records returned, which are minor gaps.

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

  Parameters5/5

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

  The schema provides only the parameter name 'field' with a generic string type and 0% description coverage. The description fully compensates by listing accepted field categories (Combat, Economy, Farming, Damage, Other) with specific values like kills, gold_per_min, last_hits, and duration, and by explaining that variations like 'gpm' and 'gold_per_min' are accepted. This goes far beyond the schema.

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

  Purpose5/5

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

  The description begins with 'Get top world record performances in a specific statistical field', which is a specific verb+resource combination that clearly defines the tool's function. It further distinguishes the tool from siblings by focusing on 'world record' and 'all-time best performances', and it provides multiple example user queries that uniquely map to this tool.

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

  Usage Guidelines4/5

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

  The description gives explicit usage context with 'Use this when users ask:' followed by six concrete example questions. It also includes a 'Common queries' section with specific calls, providing clear guidance on when to invoke the tool. However, it does not explicitly mention when not to use it or name alternative tools, so it stops 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.

• get_hero_detailsA
  4.5/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden. It discloses fuzzy matching behavior, case-insensitivity, and accepted input forms, and details the return structure. It does not mention error behavior or rate limits, but for a simple read-only lookup this is fairly transparent.

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

  Conciseness5/5

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

  The description is well-structured with 'Use this when', 'Supports', 'Args', 'Returns', and 'Examples' sections. It is appropriately detailed (about 200 words) with no redundant fluff; every sentence adds value.

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

  Completeness4/5

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

  Given the tool's simplicity and the presence of an output schema, the description is complete for typical use. It covers usage, parameter semantics, examples, and return fields. It doesn't address edge cases like unknown heroes or partial matches, but fuzzy matching is explained, so this is a minor gap.

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

  Parameters5/5

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

  Schema coverage is 0% and the schema only declares 'hero' as anyOf integer/string with no description. The description fully compensates by explaining accepted formats (display name, internal name, fuzzy match, ID) with concrete examples, making parameter semantics crystal clear.

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

  Purpose5/5

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

  The description clearly states 'Get detailed hero information by hero name or ID with fuzzy matching', which is a specific verb+resource+method. It distinguishes itself from sibling tools like get_item_details and get_aghs_details by focusing on hero data.

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

  Usage Guidelines4/5

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

  Provides explicit 'when to use' guidance with example user queries ('Use this when users ask about heroes: ...'). However, it does not mention explicit exclusions or alternative tools for hero-specific queries (e.g., get_hero_matchups), so it lacks the full 'when-not-to-use' component.

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

• get_hero_matchupsA
  4.5/5.0
  Behavior4/5

  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 discloses return format, sorting behavior, fuzzy-matching behavior, and input flexibility. It does not mention potential errors, rate limits, or authentication, but for a read-only lookup tool the described behavior is transparent and sufficient.

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

  Conciseness4/5

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

  The description is well-structured with clear sections (purpose, use cases, fuzzy matching, args, returns, example). It is somewhat verbose but each section adds value; the example output is instructive rather than redundant. It could be tightened slightly without losing clarity.

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

  Completeness5/5

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

  For a single-parameter lookup tool, the description provides comprehensive context: when to use, input semantics, output format, sorting, and a full example. The presence of an output schema is noted, but the description itself already details the return structure thoroughly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must fully compensate. It does: it explains the 'hero' parameter accepts display names, internal names, fuzzy matches, and IDs, with concrete examples like 'Pudge', 'antimage', and 86. This far exceeds the bare schema definition.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Get matchup statistics showing how a hero performs against all other heroes.' It clearly distinguishes itself from sibling tools like get_hero_details or get_hero_item_popularity by focusing on head-to-head matchup statistics. The use-case examples further reinforce the specific purpose.

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

  Usage Guidelines4/5

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

  The description explicitly lists natural-language triggers ('Which heroes counter Pudge?') and practical applications (counter-picks, draft analysis). It does not name alternative sibling tools directly, but the guidance is clear enough to know when to invoke this tool. It lacks explicit negative guidance ('do not use for X'), so it misses a 5.

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

• get_player_peersA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it discloses sorting ('Results are sorted by number of games played together'), pagination behavior ('offset: Skip first N matches'), defaults (peers_count default 5), and returns a detailed field-by-field breakdown. It doesn't cover possible errors or rate limits, but for a read-only teammate stats tool it provides substantial behavioral context.

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

  Conciseness4/5

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

  The description is lengthy but well-structured into an intro, example queries, Args, Returns, Common queries, and an Example. Each section serves a purpose for a 10-parameter tool. It could be slightly tightened, but no part feels like filler.

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

  Completeness5/5

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

  Despite having 10 parameters and no annotations or schema descriptions, the description covers all parameters, defaults, return output, and provides concrete examples. It explains sorting and pagination behavior, and the example output field list makes the result structure fully transparent. Minor ambiguity about what counts as 'recent matches' is the only gap, but overall it's highly complete.

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

  Parameters5/5

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

  Schema description coverage is 0%, making the description essential. The 'Args:' section adds meaning beyond the raw schema for every parameter, clarifying things like 'included_account_id: Get stats for SPECIFIC teammate(s) only (accepts names or IDs)' and 'limit: Number of matches to analyze (default: all recent matches).' The 'Common queries' examples show how to combine parameters, giving rich semantic grounding.

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

  Purpose5/5

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

  The description clearly states 'Get players who frequently play WITH the specified player (teammates, not opponents)' and further reinforces the scope with 'This returns players who have been ON THE SAME TEAM as the specified player.' It distinguishes from sibling tools by focusing on teammates/party members, and the example user queries ('Who does [player] play with?') make the purpose immediately obvious.

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

  Usage Guidelines4/5

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

  Explicitly says 'Use this when users ask about TEAMMATES or PARTY MEMBERS' and provides example queries. It also includes an exclusion ('not opponents'). However, it does not name alternative tools for opponent-focused queries or general stats, so it lacks explicit alternative tool guidance.

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

• get_scenarios_item_timingsA
  4.5/5.0
  Behavior4/5

  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 discloses the requirement to provide at least one parameter, supports natural language names, explains the three return modes, and provides a detailed example showing the data structure and how to interpret win rate trends. This is strong transparency for a tool with no annotations, though it does not mention potential edge cases like omitted parameters causing errors.

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

  Conciseness4/5

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

  The description is lengthy but well-organized into clear sections (purpose, use cases, args, returns, common queries, example). It is front-loaded with the primary purpose and usage examples. While some sections are verbose, every part earns its place given the tool's complexity and the need to document three modes of operation.

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

  Completeness5/5

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

  Given the complexity (2 optional parameters, 3 modes, no annotations, output schema present), the description is exceptionally complete. It fully documents the return structure for each parameter combination, provides a worked example, and interprets the data to help the agent understand the semantic meaning of win rates over time. It is more than sufficient for an agent to use the tool correctly.

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

  Parameters5/5

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

  The input schema is minimal (anyOf integer/string/null with default null) and has 0% description coverage. The description's Args section fully compensates by explaining accepted item abbreviations, hero ID/name formats, and the three combination scenarios. The note about 'at least one parameter must be provided' and the 'Common queries' examples add semantic meaning far beyond the raw schema.

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

  Purpose5/5

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

  The description clearly states 'Get win rates for heroes based on item purchase timing' with a specific verb and resource. It is distinguished from sibling tools like get_hero_item_popularity and get_scenarios_lane_roles by focusing on timing-based win rates. Numerous example queries reinforce the tool's unique purpose.

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

  Usage Guidelines4/5

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

  The description includes a 'Use this when users ask' section with 8 explicit example queries and a 'Common queries' section with concrete parameter combinations. However, it does not explicitly mention when not to use this tool or name alternative tools for exclusions, which prevents a score of 5.

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

• get_aghs_detailsA
  4.6/5.0
  Behavior4/5

  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 transparently explains fuzzy matching behavior, accepts both names and IDs, and details the exact return dictionary fields. It does not mention error handling or edge cases (e.g., unknown hero), but the provided information gives a solid behavioral model.

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

  Conciseness5/5

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

  The description is well-structured with clear sections (use cases, fuzzy matching, args, returns, examples). Every sentence provides useful information or an example, with no unnecessary filler. While longer than minimal descriptions, the added complexity of fuzzy matching and return format justifies the length.

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

  Completeness5/5

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

  For a tool with a single parameter and an output schema, the description is exceptionally complete. It covers when to use it, input formats, matching behavior, and provides a detailed breakdown of the return dictionary and examples. It leaves no significant gaps for an agent to invoke it correctly.

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

  Parameters5/5

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

  The schema provides only the parameter name 'hero' with a loose anyOf type, and schema description coverage is 0%. The description fully compensates by explaining acceptable forms (display name, internal name, fuzzy match, hero ID) with concrete examples like 'Pudge', 'antimage', and 1. This adds deep semantic meaning beyond the raw schema.

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

  Purpose5/5

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

  The description clearly states the tool gets Aghanim's Scepter and Shard upgrade details for a hero, and explicitly distinguishes it from sibling tools like get_hero_details or get_item_details by focusing specifically on Aghanim's upgrades. The verb 'Get' and resource 'Aghanim's upgrade details' are specific and unambiguous.

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

  Usage Guidelines4/5

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

  The description provides clear usage guidance: 'Use this when users ask about Aghanim's upgrades' and gives concrete example queries. It does not explicitly mention when not to use it or name alternative tools, but the context is clear enough to steer an agent correctly.

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

• get_hero_item_popularityA
  4.6/5.0
  Behavior4/5

  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 details the return structure (game phases, wins/games), explains fuzzy matching for hero names, and notes that data comes from 'thousands of matches.' It does not explicitly state read-only nature or potential errors, but for a read-only 'get' tool this is fairly transparent.

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

  Conciseness5/5

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

  The description is well-structured with sections: purpose, use cases, return format, args, and examples. Every sentence adds value, and the content is directly relevant to invoking the tool correctly. Though long, the organization and front-loaded purpose make it easy to parse.

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

  Completeness5/5

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

  For a single-parameter tool with rich output, the description is comprehensive. It fully documents the return structure, phase time ranges, and per-item statistics with examples. It also demonstrates the call format via example invocations. No important context is missing for an agent to use this tool effectively.

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

  Parameters5/5

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

  The input schema only provides a type (integer or string) for the hero parameter with no enum, and schema coverage is 0%. The description compensates thoroughly by explaining 'Hero name (display name, internal name, fuzzy match) or hero ID' with concrete examples including alias handling. This fully disambiguates the parameter beyond what the schema offers.

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

  Purpose5/5

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

  The description opens with a specific verb+resource+scope: 'Get item popularity statistics for a hero organized by game phase.' It clearly distinguishes from siblings like get_item_details (item info) or get_hero_matchups (hero matchups) by focusing on item popularity per hero. The example queries further reinforce the tool's purpose.

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

  Usage Guidelines4/5

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

  The description provides explicit 'Use this when users ask about:' with multiple concrete example queries, making the intended usage clear. It also lists 'useful for' scenarios that help the agent decide when to invoke this tool. However, it does not mention when not to use or explicitly name alternative tools, so it falls short of a full 5.

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

• get_item_detailsA
  4.6/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full transparency burden. It discloses fuzzy matching behavior, the argument format, and the return structure with field names. However, it doesn't specify error handling for unknown items, which would be helpful but not critical.

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

  Conciseness5/5

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

  The description is well-structured with sections for usage, fuzzy matching, args, returns, and examples. It's concise for the information provided—every section adds value without redundancy.

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

  Completeness5/5

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

  Given the simple single-parameter input and the detailed explanation of behavior and return fields, the description is complete for an AI agent to select and use the tool. It covers what the tool does, how to invoke it, and what to expect in response.

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

  Parameters5/5

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

  The schema provides only a type string with no description (0% coverage). The description thoroughly explains item_name with accepted formats (display name, internal name, fuzzy), provides examples, and clarifies case-insensitivity. It fully compensates for the schema gap.

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

  Purpose5/5

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

  The description uses 'Get' as a specific verb with the resource 'detailed item information by item name.' It clearly distinguishes from sibling tools focused on players, matches, and heroes. No ambiguity.

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

  Usage Guidelines4/5

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

  It explicitly states 'Use this when users ask about items' and provides three query examples. It doesn't list exclusions or alternative tools, but the scope is clear and no other sibling handles item details.

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

• get_recent_matchesA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full transparency burden. It discloses the exact number of matches (20), the sorting order (newest first), and the detailed return fields. It also includes an example output, making the behavior highly predictable. It does not cover edge cases like player-not-found errors, but for a read-only query tool, this is reasonably transparent.

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

  Conciseness5/5

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

  Although the description is long, it is well-structured with clear sections (summary, use cases, returns, args, example). Every sentence provides useful information, and the front-loaded first sentence immediately states the core purpose. The length is justified by the complexity of the return data.

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

  Completeness5/5

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

  The description is highly complete for a tool with one parameter and no annotations. It covers the tool's purpose, when to use it, the full return schema with type descriptions, common query examples, and a worked example. The only missing piece might be error handling, but the provided context is sufficient for an agent to select and invoke the tool correctly.

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

  Parameters5/5

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

  The input schema only defines player_name as a string with no description, so the description must compensate. It does so thoroughly: the 'Args' section explains player_name is 'The Dota 2 player name to search for,' and the 'Common queries' section provides concrete usage examples with actual player names, adding significant meaning beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool retrieves a player's 20 most recent Dota 2 matches with performance statistics, which is a specific verb-resource pairing. It distinguishes itself from siblings by explicitly focusing on 'recent matches' and including performance metrics, while sibling tools like get_match_details or get_player_win_loss serve different purposes.

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

  Usage Guidelines4/5

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

  The description provides an explicit 'Use this when users ask' section with concrete example queries, which is strong usage guidance. However, it does not mention when NOT to use this tool or explicitly point to alternative sibling tools, so it lacks explicit exclusions.

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

• get_player_infoA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It comprehensively discloses the output shape, including nested hero data, and implies read-only behavior. However, it leaves minor gaps such as exact-match vs fuzzy search behavior for player_name and error handling when a player is not found. Still, the disclosure is far more detailed than typical.

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

  Conciseness5/5

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

  Although the description is long, it is well-structured with clear sections and every part earns its place: purpose, usage context, return format, and an example. The example brings concrete relevance. No word is wasted on tautology.

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

  Completeness5/5

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

  The description covers purpose, usage, parameter semantics, return schema in detail, and an example. It differentiates from a large set of siblings and gives a complete picture of a straightforward read-only lookup tool. There is no missing critical context.

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

  Parameters4/5

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

  Schema coverage is 0%, so the description must compensate. It provides an Args section: 'player_name: The Dota 2 player name to search for.' This adds meaning beyond the bare string type, though it could specify match behavior (e.g., exact, partial). Sufficient for a single simple parameter.

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

  Purpose5/5

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

  The description opens with a specific verb+resource: 'Get complete Dota 2 player profile with overview statistics.' It clearly distinguishes from siblings by positioning itself as the FIRST tool for player lookups and enumerating exactly what is retrieved (profile, win/loss, top heroes). This contrasts with the many specialized sibling tools.

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

  Usage Guidelines5/5

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

  Explicit when-to-use guidance is provided: 'initial player lookups', example user queries, and the directive 'This is the FIRST tool to use when a user mentions a player.' It also references specialized tools afterward, effectively naming the alternative behavior. This is a textbook example of usage differentiation.

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

• get_player_totalsA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden and does well: it explains the return format ('List of statistical totals...each containing field, games_played, count, average'), flexible ID/natural language support, and parameter behaviors like default limit. However, it omits edge-case behaviors such as empty results, rate limiting, or the performance cost of aggregating over all available matches.

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

  Conciseness4/5

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

  The description is well-structured with headers, bullet lists, and examples, making it easy to scan. It is slightly verbose due to the extensive metric list and the 'Common queries' section partially duplicating the Example section, but the extra detail is informative rather than wasteful.

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

  Completeness5/5

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

  For a 10-parameter tool with no annotations, the description is exceptionally complete. It covers when to use, parameter semantics, output schema details, common query patterns, and a concrete example, leaving the agent fully equipped to invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the Args section compensates by documenting all 10 parameters with meaningful semantics. For example, 'hero_id: Filter to specific hero (accepts name or ID like "Rubick")' and 'lane_role: Filter by lane (accepts "mid", "carry", "pos 1-4", etc.)' add crucial usage information beyond the schema types.

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

  Purpose5/5

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

  The description opens with 'Get aggregated performance statistics across ALL tracked metrics (GPM, KDA, damage, etc.)', which clearly identifies the tool's action and scope. It further differentiates from siblings by explicitly naming get_player_win_loss and get_player_histograms as alternatives for different question types.

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

  Usage Guidelines5/5

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

  The description provides explicit usage guidance with 'Use this when users ask about AVERAGE PERFORMANCE or AGGREGATE STATS' and lists concrete example queries. It also states when NOT to use it, directing users to get_player_win_loss() and get_player_histograms() for other analyses.

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

• get_scenarios_lane_rolesA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries full responsibility. It fully discloses the varying output structure based on which parameters are provided, lists each timing entry field with types, and gives a rich example that even shows interpretation. It also notes that at least one parameter is required, adding important behavioral context.

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

  Conciseness4/5

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

  The description is long, but well-structured with clear sections (Args, Returns, Common queries, Example) and a front-loaded purpose sentence. Some example queries are repetitive, but each section adds distinct value for an agent, so the length is mostly warranted.

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

  Completeness5/5

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

  Given only two parameters, no annotations, and no schema descriptions, this description fully compensates. It covers all input combinations, return shapes for each case, field definitions, an example output, and even a sample interpretation. The agent is left with no ambiguity about invocation or results.

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

  Parameters5/5

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

  Schema coverage is 0%, but the description thoroughly documents both parameters. It explains accepted integer codes and string aliases for lane_role, hero_name ID and name formats, and provides concrete examples like '86 for Rubick' and 'Anti-Mage'. It also explains the effect of providing each parameter alone or together.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Get win rates for heroes in specific lane roles segmented by game duration.' It clearly distinguishes this from sibling tools like get_scenarios_item_timings by focusing on lane roles and game duration, and it lists concrete user query examples.

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

  Usage Guidelines4/5

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

  The description provides extensive usage guidance, including exact user questions, common query patterns, and parameter combination rules. It does not explicitly name an alternative tool for exclusion, but it makes the intended use case unmistakable through examples such as 'Which lane should I play [hero] in for short games?'

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

• request_parse_matchA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description fully carries the behavioral disclosure burden. It reveals that parsing is asynchronous ('takes time'), non-instant ('wait 1-5 minutes'), and conditional ('Not all matches can be parsed'). It also explains the return structure (status, job, error info) and warns against immediately calling get_match_details. This is exemplary transparency about latency, failure modes, and response semantics.

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

  Conciseness5/5

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

  Although the description is long, it is well-structured with clear sections (use case, extracted data, notes, Args, Returns, workflow, example). Every section earns its place: the time warning is critical, the return example clarifies the async behavior, and the workflow avoids misuse. No filler or redundancy; the length is proportionate to the tool's complexity.

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

  Completeness5/5

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

  Given the tool's async nature and the presence of an output schema, the description covers all necessary context: how to trigger, what to expect in the response, how long to wait, potential errors, and the next step in the workflow. It even provides a concrete example output. The description is complete enough for an AI agent to select and invoke the tool correctly without further clarification.

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

  Parameters4/5

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

  The input schema only specifies match_id as an integer with no description (coverage 0%). The description compensates with 'match_id: The match ID to parse (e.g., 8123456789)', adding an example and the semantic concept of 'match ID'. This adds meaning beyond the raw schema, though the parameter is simple and the extra explanation is minimal.

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

  Purpose5/5

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

  The description opens with a clear, specific action: 'Submit a request to parse a specific match for detailed replay analysis.' It uses the verb 'submit' and the resource 'match', distinguishing this from the sibling get_match_details by positioning it as the request initiation step. The trigger phrase 'Parse match [match_id]' also directly maps to user intent.

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

  Usage Guidelines4/5

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

  The description provides explicit when-to-use guidance: 'Use this when users ask: Parse match...'. It also details a common workflow (request, wait 1-5 minutes, then get_match_details), clearly indicating this tool is a prerequisite for the sibling tool. However, it does not explicitly state when NOT to use this tool (e.g., when match data is already parsed), though the workflow implicitly covers that.

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

• get_heroes_playedA
  4.8/5.0
  Behavior4/5

  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 sorting order ('sorted by games played, descending'), pagination behavior (offset), filtering effects, and the exact return structure. However, it does not explicitly state that the operation is read-only or mention potential rate limits, but these are implicitly obvious for a stats query.

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

  Conciseness5/5

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

  The description is long but well-structured with clear headings (Args, Returns, Common queries, Example). Every sentence provides useful information—including example queries and a concrete JSON output—without fluff. It is front-loaded with the core purpose, so agents can quickly grasp functionality.

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

  Completeness5/5

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

  Given 10 parameters, no annotations, and an output schema whose presence is indicated, the description is remarkably complete. It covers all parameter semantics, return fields, common usage patterns, and a full example output. It leaves no significant gaps for an agent to make incorrect assumptions.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description's Args section compensates fully by explaining every parameter's meaning, acceptable types, and examples (e.g., lane_role accepts 'mid', 'carry', offlane', 'pos 1-4'; with_hero_id accepts names or IDs). It adds substantial value beyond the bare schema.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Get detailed statistics for all heroes a player has played'. It clearly distinguishes this tool from sibling get_player_win_loss by stating 'For simple win/loss totals without hero breakdown, use get_player_win_loss() instead.'

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

  Usage Guidelines5/5

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

  The description provides explicit usage context with example user queries (e.g., 'What heroes does [player] play?') and demonstrates when to use this tool. It also names the alternative tool for simpler queries, fulfilling the when-to-use vs. alternatives criterion.

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

• get_match_detailsA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and excels. It discloses the automatic parse-status detection, explains the two distinct return structures (parsed/unparsed), and notes the prerequisite for unparsed matches. The behavior is fully transparent and includes practical details like 'wait a few minutes.'

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

  Conciseness4/5

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

  The description is well-structured with clear headers, bullet lists, and examples, and the purpose is front-loaded. However, it is notably long, and the extensive return-structure documentation may be redundant given an output schema exists. Still, the organization keeps it scannable.

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

  Completeness5/5

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

  The description addresses the core complexity: conditional behavior based on parse status, the prerequisite parse workflow, and detailed semantics of both response shapes. It also includes common queries and examples, leaving minimal ambiguity for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  Schema coverage is 0% for match_id, so the description must compensate. It does so by defining match_id as 'The match ID to retrieve' with a concrete example (8123456789). For a single integer parameter, this is sufficient, though it doesn't add constraints (e.g., format/range).

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

  Purpose5/5

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

  The description begins with a clear, specific verb+resource combination: 'Get comprehensive details for a specific match.' It further distinguishes itself from siblings like request_parse_match and get_hero_details by focusing on match-level data and directly listing user query examples that trigger its use.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance through example user queries, and clearly differentiates from the alternative request_parse_match: 'For matches that aren't parsed yet, use request_parse_match() first, wait a few minutes, then call this function.' This is a concrete workflow with an alternative named.

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

• get_player_win_lossA
  4.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden, and it does well: it states the return format ('Dictionary with exactly two fields: win and lose'), mentions it returns ONLY win/loss counts, and notes support for both IDs and natural language. It could add edge-case behavior (e.g., no matches found, invalid hero name), but it is already highly transparent for a read-only query tool.

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

  Conciseness5/5

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

  Though lengthy, the description is well-structured with clear sections: purpose, when-to-use, parameter details, return values, and examples. Every paragraph earns its place; the length is justified by the tool's nine flexible parameters and the need to distinguish between similar sibling tools. It is front-loaded with the core purpose.

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

  Completeness5/5

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

  The description covers all nine parameters, return format, common usage scenarios, and explicit alternatives. It is complete enough for an agent to select and invoke the tool correctly without needing external documentation. The output schema is simple, and the description fully complements it.

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

  Parameters5/5

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

  The schema has no parameter descriptions, but the description thoroughly explains every parameter, including accepted types and values (e.g., lane_role integer-to-string mapping, hero_id integer or name, included_account_id as string or list). It also provides common query examples for each meaningful filter, fully compensating for the 0% schema coverage.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Get simple win/loss counts for a player with optional filters.' It explicitly distinguishes itself from sibling tools like get_heroes_played and get_player_totals, and the tool name itself is clear. 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.

  Usage Guidelines5/5

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

  The description explicitly states when to use the tool ('Use this when users ask about WIN RATES or WIN/LOSS RECORDS') and provides concrete example queries. It also names alternatives ('use get_heroes_played() instead', 'use get_player_totals() instead'), making the decision boundary crystal clear.

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

• get_benchmarksA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explains the return is percentile-based, shows a detailed example output with percentiles, and describes how to interpret results (e.g., 'If a player has 460 GPM on Rubick, they're performing around the 75th percentile'). This is exemplary transparency.

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

  Conciseness4/5

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

  The description is well-structured with clear sections and front-loaded purpose, but it is somewhat lengthy. There is minor redundancy between the initial bullet list of queries and the later 'Common queries' section. Still, every section contributes useful information, and the example output earns its place.

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

  Completeness5/5

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

  For a one-parameter tool with no annotations, the description is remarkably complete. It covers input formats, output structure, common metrics, example usage, and interpretation. Even though an output schema exists, the description's Returns section adds clarity about percentile semantics and metric names.

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

  Parameters5/5

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

  The schema only defines hero_id as integer or string with zero description. The tool description compensates fully by stating it accepts hero IDs (e.g., 86) or hero names (e.g., 'Rubick', 'Anti-Mage'), giving examples and clarifying the flexible input format. This adds substantial meaning beyond the raw schema.

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

  Purpose5/5

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

  The description opens with a specific verb+resource: 'Get statistical benchmarks for a hero' and clarifies it provides 'average performance metrics across all skill levels.' This clearly distinguishes it from sibling tools like get_player_histograms or get_player_totals by focusing on percentile-based benchmarks for a single hero.

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

  Usage Guidelines5/5

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

  Explicitly lists example user queries (e.g., 'What are the average stats for [hero]?') and even recommends a workflow: 'First get player stats with get_player_totals(), then compare to benchmarks from this function.' This names an alternative tool and provides sequencing, exceeding the basic 'when to use' requirement.

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

• get_player_histogramsA
  5/5.0
  Behavior5/5

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

  With no annotations, the description fully carries the behavioral transparency burden. It explains what the tool returns (histogram buckets), how values are grouped (ranges or exact values), the inclusion of win_rate, and nuances like 'Higher performance levels often correlate with higher win rates.' It also mentions flexible querying ('Supports both IDs and natural language'), pagination via offset, and the having threshold.

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

  Conciseness5/5

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

  Although long, the description is well-structured with clear sections: purpose, usage, exclusions, arguments, return values, and examples. Every section earns its place given 11 parameters and a nuanced output format. The example output is illustrative and not fluff.

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

  Completeness5/5

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

  The description is complete for a complex tool: it covers all 11 parameters, explains the return value semantics despite having an output schema, and provides concrete examples. It leaves no obvious gaps for the agent to select and invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description's Args section compensates fully. It explains every parameter, gives alternative names for fields (e.g., 'gpm' or 'gold_per_min'), and clarifies that hero/account parameters accept both IDs and names. This goes far beyond the bare schema.

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

  Purpose5/5

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

  The description opens with a specific verb+resource: 'Get the DISTRIBUTION of a specific statistic across matches (performance consistency analysis).' It clearly distinguishes itself from siblings like get_player_totals and get_player_win_loss by focusing on distributions, ranges, and consistency.

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

  Usage Guidelines5/5

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

  Provides explicit when-to-use criteria with real user queries (e.g., 'How often does [player] get 10+ kills?') and explicit when-not-to-use instructions with named alternatives ('use get_player_totals() instead', 'use get_player_win_loss() instead'). This is model-level guidance.

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