Server Quality Checklist

Tool Scores

• tm_list_assetsA
  4/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, indicating a safe, non-destructive, and repeatable read operation. The description adds context by specifying the return format (array of symbol, name, chain, address), which is valuable beyond annotations, though it doesn't detail rate limits or authentication needs.

  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, followed by clear Arg and Return sections. Every sentence earns its place by efficiently conveying essential information without redundancy, making it appropriately sized 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 low complexity (one optional parameter) and rich annotations covering safety and behavior, the description is mostly complete. It specifies the return format, which compensates for the lack of an output schema. However, it could improve by mentioning authentication or rate limits, though annotations provide sufficient context for a read-only operation.

  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 100%, with the schema fully documenting the optional 'chain' parameter and its enum values. The description adds minimal value beyond the schema by restating the filter purpose, but doesn't provide additional syntax or format details, aligning with the baseline score when schema coverage is high.

  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 verb 'List' and the resource 'tokens available for trading on True Markets', making the purpose specific. It distinguishes from siblings like tm_get_balances (which retrieves user balances) and tm_get_price (which fetches pricing data) by focusing on available trading tokens rather than user-specific or price information.

  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 for listing tokens, but does not explicitly state when to use this tool versus alternatives. For example, it doesn't clarify if this should be used before trading or as a reference, nor does it mention exclusions or direct comparisons to siblings like tm_get_rades or tm_prepare_transfer, leaving usage context inferred rather than explicit.

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

• tm_get_profileA
  4.2/5.0
  Behavior4/5

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

  Annotations already cover key behavioral traits (read-only, open-world, idempotent, non-destructive). The description adds value by specifying the return format ('{ email, wallets: [{ chain, address }] }'), which is useful context not provided in annotations. No contradiction with annotations.

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

  Conciseness5/5

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

  The description is front-loaded with the core purpose in the first sentence, followed by a concise return format specification. Both sentences earn their place by providing essential information without waste.

  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 (0 parameters, no output schema), rich annotations, and clear return format in the description, it is nearly complete. A minor gap is lack of explicit usage guidance versus siblings, but overall it provides sufficient context for an agent to use it 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?

  The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately does not discuss parameters, earning a baseline score of 4 for not adding unnecessary information.

  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 ('Get') and resource ('the authenticated user's profile'), including what data is retrieved ('email and wallet addresses'). It distinguishes from siblings like tm_get_balances (which focuses on balances) and tm_get_price/quote (which are market-related).

  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 for retrieving profile data, but does not explicitly state when to use this tool versus alternatives (e.g., no guidance on when profile info is needed vs. balances or assets). It provides basic context but lacks explicit when/when-not instructions or named alternatives.

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

• tm_get_balancesA
  4.3/5.0
  Behavior4/5

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

  The description adds valuable context beyond annotations: it specifies the scope ('across all chains'), mentions authentication requirement ('authenticated user'), and describes the return format. While annotations already declare readOnlyHint=true, destructiveHint=false, etc., the description provides operational context about what data is returned and authentication needs.

  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 front-loaded with the core purpose in the first sentence, followed by clear parameter and return value sections. Every sentence earns its place with zero wasted words, making it easy for an AI agent to quickly understand the tool's function.

  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 low complexity (one optional parameter), comprehensive annotations covering safety and behavior, and clear description of return values, this description is complete enough. No output schema exists, but the description adequately explains what's returned, making it sufficient for agent understanding.

  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?

  With 100% schema description coverage, the schema already fully documents the single optional parameter. The description adds minimal value beyond the schema by mentioning the filter capability but doesn't provide additional syntax, format details, or usage examples beyond what's in 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 specific action ('Get token balances'), target resource ('for the authenticated user'), and scope ('across all chains'). It distinguishes from siblings like tm_get_price (price data) and tm_list_assets (asset listing) by focusing on user-specific balance retrieval.

  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 about when to use it (to get token balances for authenticated user), but doesn't explicitly state when NOT to use it or name specific alternatives. It implies usage for balance queries vs. siblings like tm_execute_trade for trading or tm_get_profile for profile data.

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

• tm_get_priceA
  4.3/5.0
  Behavior4/5

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

  Annotations cover read-only, open-world, idempotent, and non-destructive traits. The description adds valuable context beyond this: it specifies 'zero-cost quote' (implying no fees), 'Resolves token symbols automatically' (behavioral detail), and 'Does NOT require an API key — only auth token' (auth needs). This enriches understanding without contradicting annotations.

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

  Conciseness5/5

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

  The description is front-loaded with the core purpose, followed by key behavioral details and a clear Args/Returns structure. Every sentence adds value (e.g., symbol resolution, auth info), with no wasted words, making it efficient and well-organized.

  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 low complexity (2 parameters, no output schema), rich annotations, and 100% schema coverage, the description is complete. It covers purpose, usage context, behavioral traits, and return format, providing all necessary information for an agent to invoke it correctly without redundancy.

  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 100%, so the schema already documents parameters fully. The description adds minimal semantics: it reiterates token symbol examples and chain options, but does not provide additional meaning (e.g., format details or edge cases). Baseline 3 is appropriate as the schema carries the burden.

  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 ('Get the current price') and resource ('token in USDC'), distinguishing it from siblings like tm_execute_trade (trading) or tm_get_balances (balance checking). It specifies the method ('by running a zero-cost quote'), making the purpose unambiguous and distinct.

  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 price queries with automatic symbol resolution and no API key requirement. However, it does not explicitly mention when not to use it or name alternatives (e.g., tm_get_quote might be similar), leaving some ambiguity in sibling differentiation.

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

• tm_execute_transferA
  4.4/5.0
  Behavior4/5

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

  Annotations cover readOnlyHint=false, destructiveHint=true, etc., but the description adds 'Irreversible,' which is crucial behavioral context beyond annotations. It doesn't contradict annotations, as destructiveHint=true aligns with 'Irreversible.'

  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?

  Two sentences with zero waste: first states purpose and key behavior, second lists returns. It's front-loaded with essential information and appropriately sized.

  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 (irreversible, destructive), annotations provide safety info, but no output schema exists. The description lists return fields, compensating well. However, it could mention prerequisites like auth or rate limits.

  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 100%, so the schema already documents the single parameter. The description adds minimal value by referencing tm_prepare_transfer, but no additional syntax or format details 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 verb ('Execute') and resource ('a prepared transfer'), specifying it's for transfers prepared with tm_prepare_transfer. It distinguishes from siblings like tm_execute_trade (trades) and tm_prepare_transfer (preparation).

  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?

  It explicitly states when to use ('Execute a transfer prepared with tm_prepare_transfer') and implies when not to use (e.g., for trades, balances, or unprepared transfers). The context with sibling tools like tm_prepare_transfer provides clear alternatives.

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

• tm_prepare_transferA
  4.4/5.0
  Behavior4/5

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

  The description adds valuable context beyond annotations: it clarifies this is a preparation step that returns a transfer_id for later execution, which explains why readOnlyHint=true despite 'transfer' terminology. It doesn't contradict annotations (which indicate read-only, non-destructive, non-idempotent, open-world). However, it could mention rate limits or authentication requirements to reach a perfect score.

  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: a clear purpose statement in the first sentence, followed by a concise explanation of the workflow relationship, then organized parameter and return value sections. Every sentence earns its place with zero redundancy or fluff.

  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?

  For a preparation tool with read-only annotations and no output schema, the description is nearly complete. It explains the purpose, workflow relationship, parameters, and return structure. It could be slightly more complete by mentioning authentication requirements or error conditions, but covers the essential context well given the annotations.

  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?

  With 60% schema description coverage, the description adds minimal value beyond the schema. It lists parameters but provides no additional semantic context about format requirements (e.g., address validation, decimal precision), token symbol vs contract address distinctions, or practical examples. The schema already documents each parameter adequately.

  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 ('Prepare a transfer'), target resource ('to an external wallet address'), and output purpose ('Returns transfer details and a transfer_id for execution with tm_execute_transfer'). It explicitly distinguishes from its sibling tool tm_execute_transfer by indicating this is a preparation step rather than execution.

  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 guidance on when to use this tool ('Prepare a transfer') versus its alternative ('for execution with tm_execute_transfer'). It establishes a clear workflow where this tool is used first to prepare, then the sibling tool executes. No other alternatives are needed given this specific two-step process.

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

• tm_execute_tradeA
  4.5/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond annotations: it explains the irreversible nature of the trade (reinforcing destructiveHint=true), mentions signing with API keys (security context), and specifies time constraints (60-second validity). While annotations cover safety aspects, the description provides operational details that help the agent use the tool correctly.

  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 structured with critical information front-loaded: purpose, prerequisites, and warnings in the first sentences. Every sentence earns its place by providing essential guidance. The Args/Returns section is clear 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?

  For a destructive trade execution tool with no output schema, the description provides excellent completeness: it explains the irreversible nature, prerequisites, timing constraints, and even outlines the return structure. Given the complexity and risk level, this description gives the agent everything needed to use the tool safely and correctly.

  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?

  With 100% schema description coverage, the schema already documents the single parameter thoroughly. The description adds minimal extra context by linking quote_id to tm_get_quote, but doesn't provide additional semantic meaning beyond what's in the schema. This meets the baseline for high 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 clearly states the specific action ('Execute a trade') and resource ('using a quote_id from tm_get_quote'), distinguishing it from siblings like tm_execute_transfer (transfers) and tm_get_quote (quotes only). It provides a complete picture of the tool's function beyond just the title.

  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 states when to use ('Only call this after inspecting the quote from tm_get_quote') and includes critical prerequisites ('quote must be less than 60 seconds old and have no issues'). It also distinguishes from tm_get_quote by specifying this is the execution step after obtaining a quote.

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

• tm_get_quoteA
  4.7/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond annotations. While annotations indicate readOnlyHint=true (non-destructive) and openWorldHint=true, the description specifies the 60-second expiration window ('quote_id that can be passed to tm_execute_trade within 60 seconds'), which is critical for timing behavior. It also mentions inspecting 'issues' like insufficient balance, adding practical constraints. No contradiction with annotations exists.

  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 and front-loaded: the first sentence states the core purpose, followed by critical usage guidelines, and then details on parameters and returns. Every sentence serves a clear purpose—no wasted words. The bullet-point format for Args and Returns improves readability without verbosity.

  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 complexity (trade quoting with financial implications) and the absence of an output schema, the description provides comprehensive context. It fully documents the return structure, including all fields like quote_id, you_pay, you_receive, fee, and expiration details. This compensates for the lack of structured output schema, ensuring the agent understands what to expect.

  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 100% schema description coverage, the baseline is 3. The description adds meaningful context: it explains the purpose of qty_unit with defaults ('default: "quote" for buy, "base" for sell'), clarifies that amount is a 'decimal string', and provides examples for token ('SOL, ETH'). This enhances understanding beyond the schema's technical definitions.

  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 explicitly states the purpose: 'Request a quote for buying or selling a token.' It specifies the verb ('Request a quote') and resource ('token'), and distinguishes it from sibling tools like tm_execute_trade by emphasizing this is a preparatory step. The description clearly differentiates this tool from tm_get_price by focusing on actionable quotes rather than just price information.

  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 guidelines: 'Always call this BEFORE tm_execute_trade. Inspect the quote (price, fee, issues) and only execute if acceptable.' It names the alternative tool (tm_execute_trade) and specifies when to use this tool versus when to proceed with execution. The context of solving 'the price uncertainty problem' further clarifies its role.

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