Server Quality Checklist

Tool Scores

• defi_overviewA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses key behavioral traits: the tool returns specific data types (TVL, chains, protocols, yields), has tiered functionality (FREE vs PRO), and mentions risk grades for yields. However, it doesn't cover important aspects like rate limits, authentication requirements, data freshness, or error conditions. The description adds value but doesn't fully compensate for the lack of annotations.

  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 perfectly structured and concise. It starts with the core purpose, lists return values clearly, then explains tier differences efficiently. Every sentence adds value: the first defines scope, the second enumerates returns, the third explains tier limitations. No wasted words or redundancy.

  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 has an output schema (so return values don't need description), no annotations, and simple parameters, the description provides good contextual completeness. It covers purpose, return data types, and tier limitations. The main gap is lack of explicit parameter documentation, but for a single optional parameter tool with output schema, this is reasonably complete.

  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 has 1 parameter with 0% description coverage, so the description must compensate. While it doesn't explicitly mention the 'chain' parameter, the description implies filtering capability through the mention of 'TVL by top 10 chains' and the tier structure. For a single optional parameter tool, this provides adequate semantic context, though not explicit parameter documentation.

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

  Purpose4/5

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

  The description clearly states the tool provides a 'big-picture DeFi dashboard' with specific metrics like total TVL, TVL by chains/protocols, pool counts, and yields. It distinguishes itself from siblings by offering aggregated overview data rather than specific analysis functions like 'analyze_pool' or 'calculate_impermanent_loss'. However, it doesn't explicitly name the verb (e.g., 'retrieve' or 'fetch') which prevents a perfect score.

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

  Usage Guidelines3/5

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

  The description implies usage context through the FREE/PRO tier distinction, suggesting this tool is for getting comprehensive DeFi market overviews. However, it doesn't explicitly state when to use this versus alternatives like 'discover_yields' for yield-focused queries or 'track_whales' for whale activity. The tier information provides some guidance but not explicit when/when-not instructions.

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

• analyze_poolA
  3.9/5.0
  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 effectively describes the tool's behavior by detailing the comprehensive return data (e.g., full pool data, APY trends, risk grade breakdown) and explicitly states the PRO requirement and API key need, which are crucial for usage. However, it doesn't mention potential limitations like rate limits or error conditions.

  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 front-loaded with the core purpose ('Deep analysis of a specific DeFi pool'), followed by a bullet-like list of return values and a clear requirement statement. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.

  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 complexity (deep analysis with multiple return aspects), no annotations, and an output schema exists (so return values don't need full explanation in the description), the description is mostly complete. It covers the analysis scope, return details, and prerequisites. However, it could benefit from more explicit differentiation from sibling tools to enhance contextual understanding.

  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 has 0% description coverage, so the description must compensate. It doesn't explicitly mention the 'pool_id' parameter, but the context ('specific DeFi pool') implies a pool identifier is needed. Since there's only one parameter, the description's focus on analysis scope provides adequate semantic context, though it could be more direct about the parameter's role.

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

  Purpose4/5

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

  The description clearly states the tool performs 'Deep analysis of a specific DeFi pool' with a specific verb ('analyze') and resource ('DeFi pool'), distinguishing it from siblings like 'defi_overview' (general overview) or 'risk_score' (single metric). However, it doesn't explicitly differentiate from 'simulate_profit' or 'calculate_impermanent_loss' which might overlap in some functionality.

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

  Usage Guidelines3/5

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

  The description implies usage through context ('PRO ONLY — requires PROFITSPOT_API_KEY') and the detailed return values suggest it's for comprehensive analysis, but it doesn't explicitly state when to use this vs. alternatives like 'defi_overview' for summaries or 'risk_score' for just risk assessment. The PRO requirement is a usage constraint, not a comparative guideline.

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

• track_whalesA
  4.1/5.0
  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 effectively describes key traits: it's a detection tool (implies read-only), requires a baseline establishment, uses APY-change heuristics, and has a PRO requirement with API key. It also mentions the reporting format (pool, direction, amount, etc.), adding valuable context beyond basic functionality.

  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 and front-loaded, starting with the core purpose. Each sentence adds value: detection criteria, reporting details, usage sequence, heuristics, and requirements. It avoids redundancy, though it could be slightly more concise by integrating some details more tightly.

  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 complexity (detection with heuristics and baselines), no annotations, and an output schema (which handles return values), the description is fairly complete. It covers purpose, usage flow, behavioral traits, and requirements. However, it lacks explicit error handling or rate limit details, which could enhance completeness for a PRO tool.

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

  Parameters3/5

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

  The schema has 3 parameters with 0% description coverage, so the description must compensate. It mentions 'TVL changed by >$500K' (mapping to min_tvl_change default) and implies time-based detection, but does not explicitly explain 'chain' or 'timeframe' parameters. The description adds some meaning (e.g., threshold and heuristic context) but does not fully cover all parameters, resulting in a baseline score.

  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's purpose: 'Detect large capital movements (whale activity) across DeFi pools.' It specifies the exact threshold (>$500K TVL change) and distinguishes itself from siblings like 'analyze_pool' or 'defi_overview' by focusing on capital flow detection rather than general analysis or overview.

  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 context on when to use this tool: for detecting whale activity based on TVL changes and APY correlations. It mentions 'First call establishes a baseline; subsequent calls detect actual changes,' guiding sequential usage. However, it does not explicitly state when NOT to use it or name alternatives among siblings, though the focus on capital movements implies differentiation from tools like 'calculate_impermanent_loss' or 'simulate_profit.'

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

• calculate_impermanent_lossA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it's a calculation tool ('pure math'), has no cost ('ALWAYS FREE'), requires no external calls ('no API call needed'), and describes what it returns (IL in USD/percentage, value comparisons, net gain/loss with fees). It doesn't mention error handling or performance characteristics.

  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?

  Perfectly front-loaded with the core purpose first, followed by supporting details in logical order. Every sentence earns its place: first states what it calculates, then explains inputs, then lists outputs, and ends with implementation details. Zero wasted words in 4 concise sentences.

  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 has an output schema (so return values don't need description), no annotations, and moderate complexity, the description is quite complete. It explains the calculation's purpose, inputs, multiple outputs, and implementation characteristics. The main gap is incomplete parameter documentation given 0% schema coverage.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate but only partially does. It explains that parameters are 'price change percentages for both tokens' which clarifies token_a_price_change and token_b_price_change, but doesn't mention the investment_amount parameter or its default value. The description adds some meaning but leaves one parameter undocumented.

  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 specific action ('calculate exact impermanent loss'), the resource ('for a 50/50 LP pair'), and distinguishes from siblings by focusing on IL calculation rather than analysis, discovery, simulation, or tracking. It provides exact scope details like USD/percentage outputs and comparison metrics.

  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 implies usage context for evaluating liquidity pool performance with price changes, but doesn't explicitly state when to use this vs alternatives like 'simulate_profit' or 'analyze_pool'. It does specify it's 'ALWAYS FREE — pure math, no API call needed' which provides helpful usage context about cost and implementation.

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

• risk_scoreA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well: it discloses the API key requirement (auth needs), explains what gets returned (overall grade + breakdown scores with explanations), and describes different behaviors for pools vs protocols. It doesn't mention rate limits or error conditions, but provides substantial behavioral context beyond basic functionality.

  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 efficiently structured: first sentence states core purpose, second describes return format, third explains protocol-specific behavior, fourth notes API requirement. Every sentence adds value with zero wasted words, and key information (purpose and PRO requirement) is front-loaded appropriately.

  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 complexity (risk scoring with multiple dimensions), no annotations, but with an output schema present, the description is mostly complete. It explains the scoring components, different behaviors for pools vs protocols, and authentication requirements. The output schema will handle return value details, so the description appropriately focuses on behavioral context. It could mention error cases or limitations.

  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?

  With 0% schema description coverage for 2 parameters, the description compensates well by explaining that 'pool_id' is for 'specific pool' and 'protocol' is for 'entire protocol', and that for protocols it 'scores the top pools and returns an aggregate grade'. This adds meaningful semantic context about how each parameter affects the tool's behavior, though it doesn't specify format requirements for these string parameters.

  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 'Get risk grade (A-F) for a specific pool or entire protocol' with specific verb ('Get'), resource ('risk grade'), and scope ('pool or entire protocol'). It distinguishes from siblings like 'analyze_pool' or 'defi_overview' by focusing specifically on risk scoring with letter grades and detailed breakdown components.

  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 context: use for risk assessment of pools or protocols, with different behaviors for each (aggregate grade for protocols). It mentions 'PRO ONLY — requires PROFITSPOT_API_KEY' as a prerequisite. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools.

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

• simulate_profitA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it describes the Ornstein-Uhlenbeck APY model components, mentions it runs 1,000 simulations, specifies the return format (optimistic/base/bearish scenarios with detailed metrics), and notes the PRO requirement and API key need. It doesn't mention rate limits or error handling, but covers core operational behavior.

  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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by model details, simulation count, return format, and requirements. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.

  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 complexity (Monte Carlo simulation with multiple model factors), no annotations, and an output schema (which handles return values), the description is largely complete. It covers purpose, methodology, scale, output structure, and prerequisites. A minor gap is lack of explicit error cases or performance characteristics, but it provides sufficient context for effective use.

  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 description coverage is 0%, so the description must compensate. While it doesn't explicitly list parameters, it implies their semantics through context: 'pool_id' is referenced as 'specific pool', 'investment' and 'days' are implied by 'Project returns' and simulation duration, and 'compound' relates to return calculations. This adds meaningful context beyond the bare schema, though not exhaustive parameter details.

  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's purpose with a specific verb ('Project returns') and resource ('for a specific pool'), distinguishing it from siblings like 'analyze_pool' or 'risk_score' by specifying Monte Carlo simulation methodology. It explicitly mentions what the tool does beyond basic analysis.

  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 context for when to use this tool (projecting returns via simulation) and mentions 'PRO ONLY — requires PROFITSPOT_API_KEY' as a prerequisite. However, it doesn't explicitly state when not to use it or name specific alternatives among the sibling tools, though the simulation focus implies differentiation.

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

• discover_yieldsA
  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 effectively describes key behavioral traits: the tool returns a sorted list with specific fields, discloses tier limitations (FREE vs PRO with result limits and risk filtering differences), and mentions the scope (86 chains, 6,500+ pools). It lacks details on rate limits, authentication needs, or error handling, but provides substantial operational context.

  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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by filtering details, return values, and tier limitations. Every sentence adds value—no redundancy or fluff—making it efficient and well-structured for quick comprehension.

  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 (5 parameters, no annotations, but with an output schema), the description is complete enough. It covers purpose, parameters, return format, and behavioral constraints (tier differences). The output schema likely details the return structure, so the description need not exhaustively explain return values, and it adequately addresses gaps from missing annotations.

  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 compensate fully. It does so by explaining all 5 parameters' semantics: chain filtering, minimum TVL, minimum APY, maximum risk grade (with scale A-F), and implicitly limit through tier details. It adds meaning beyond the schema by clarifying risk grade values, tier impacts on filtering, and default behaviors (e.g., FREE tier limitations).

  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's purpose with specific verbs ('discover top DeFi yield opportunities') and resources ('across 86 chains and 6,500+ pools'), distinguishing it from siblings like analyze_pool (specific analysis) or defi_overview (general overview). It explicitly defines the scope as discovery of opportunities rather than analysis or simulation.

  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 context for when to use this tool—for discovering yield opportunities with filtering capabilities. It implicitly distinguishes from siblings by focusing on discovery rather than analysis (analyze_pool), calculation (calculate_impermanent_loss), or simulation (simulate_profit). However, it does not explicitly state when NOT to use it or name specific alternatives among siblings.

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