Server Quality Checklist

Tool Scores

• evm_address_historyA
  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 transparency burden. It discloses a key precondition ('requires synced address'), cursor-based pagination behavior ('use nextStartingAfter from response as startingAfter'), and credit costs per action/blockchain. It does not detail auth or error behavior, but the query-only nature is strongly implied by 'Query' and the list/get actions.

  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 bullet lists for actions, networks, and credits. Every section earns its place, though the credit matrix is extensive and could be seen as slightly verbose for initial tool selection.

  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 (9 parameters, 6 actions, multiple networks) and no output schema, the description covers the essential operational details: supported actions, blockchain/network compatibility, pagination, and cost. It does not describe the response shape beyond the cursor and credit headers, which 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?

  Although the schema already documents every parameter, the description adds substantial meaning by mapping actions to supported blockchains, blockchain to networks, and explaining the pagination cursor relationship. This goes far beyond the schema's enum lists and directly helps an agent choose valid parameter combinations.

  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 opening line 'Query EVM address full history' uses a specific verb and resource, clearly distinguishing it from non-EVM tools like utxo_address_history. The subsequent action list (get-statistics, list-transactions, list-token-transfers, etc.) further clarifies the exact scope of the 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 provides strong usage context: it states the prerequisite ('requires synced address'), the supported actions, and the exact blockchain/network combinations. It does not explicitly name alternatives or exclusions, but the 'EVM' qualifier and sibling tool names make the intended use clear.

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

• system_infoA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description must disclose behavioral traits. It explicitly states 'no API call, no credits consumed', indicating a read-only, side-effect-free operation. It also details what each action returns (e.g., 'credit charging structure', 'webhook mechanics'), giving insight into behavior. However, it does not explicitly mention idempotency, authentication requirements, or error behavior, but these are less relevant for a reference 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?

  The description is well-structured and appropriately sized. It front-loads the core purpose in the first sentence, then uses bullet points to list actions efficiently. Every sentence adds value, and the format improves scannability. There is no redundancy or unnecessary 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?

  Given the tool's complexity (2 params, no output schema), the description is highly complete: it enumerates all five actions and describes the content of each. It covers the 'context' parameter's behavior indirectly by mentioning it only in the schema. While it does not specify response format or error handling, for a reference documentation tool this is sufficient and the description fully supports agent usage.

  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 schema covers both parameters (action, context) at 100%, so baseline is 3. The description adds significant meaning by explaining what each enum value of 'action' provides, e.g., 'blockchains — Supported blockchains, networks, products per chain, denominations, fiat currencies'. This goes beyond the schema's simple 'Reference topic to retrieve' and provides richer semantic context.

  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 provides CryptoAPIs reference documentation with no API call or credits consumed, and lists five specific actions (blockchains, errors, credits, callbacks, limits). This distinguishes it from sibling tools like manage_address or history tools, which are operational. The verb 'retrieve' is implied and the resource (reference topics) is explicit.

  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 for obtaining reference information, emphasizing 'no API call, no credits consumed' which positions it as a safe exploratory tool. It does not explicitly name alternatives or state when not to use it, but the context is clear given its reference nature and the sibling tools are operational. The listing of actions provides a direct way to decide which action to invoke.

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

• utxo_address_historyA
  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 the full burden. It discloses pagination behavior (cursor vs offset), the prerequisite of a synced address, and credit costs per action/blockchain. It does not explicitly state that the tool is read-only, but 'Query' implies that, and the credit information adds behavioral context beyond a simple read operation. It lacks explicit statements about side effects, but for a query tool this is not a major gap.

  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 structured with bullet points and sections (Pagination, Actions, Blockchain -> Networks, Credits), making it easy to scan. The main purpose is front-loaded in the first line. While it is fairly long, the density of useful information justifies the length, and each section serves a distinct practical purpose.

  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—10 parameters, 4 actions, 6 blockchains, varying pagination schemes, and no output schema—the description covers the essential context comprehensively: supported combinations, pagination rules, and credit costs. It lacks return value details, but for a history query tool this is partially implied. The description is complete enough for an agent to select the appropriate action and parameters.

  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 has 100% coverage, but the description adds significant cross-cutting semantics: it maps each action to supported blockchains, explains which pagination parameters apply to which action, and specifies that 'list-transactions-by-timestamp' requires the timestamp parameter. This goes well beyond the individual schema descriptions, making the parameter choices and combinations 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 the tool's purpose: "Query UTXO address full history" with the prerequisite "requires synced address." The verb 'Query' and the specific resource 'UTXO address full history' distinguish it from sibling tools like evm_address_history, and the detailed action list further specifies what it does.

  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 usage context by listing which actions support which blockchains, the pagination method for each action, and the requirement for a synced address. It does not explicitly mention alternatives or exclusions (e.g., 'use evm_address_history for EVM chains'), but the action/blockchain compatibility matrix serves as clear guidance for when to use this tool and which sub-actions to choose.

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

• manage_addressA
  4.6/5.0
  Behavior5/5

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

  Despite no annotations, the description discloses critical behaviors: the confirmation requirement for sync/activate/delete (returning a preview token instead of immediate execution), cursor pagination mechanics, and indicative credit costs. This goes well beyond the schema's parameter descriptions.

  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 structured with clear sections and bullet points, front-loading the main purpose. Each piece of information (actions, networks, confirmation, credits) justifies its place, avoiding 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's complexity (four actions, many networks, confirmation flow), the description covers essential operational details: action-specific parameter needs, network mappings, pagination, and credits. It lacks response format details, which would be useful since there's no output schema, but is otherwise sufficient.

  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 schema covers all parameters (100% coverage), but the description adds conditional requirements (e.g., 'address' required for sync/activate/delete) and explains the pagination parameter usage. It also clarifies the context of blockchain-network mappings.

  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 'Manage synced addresses for Address History APIs', a clear verb-resource pair, then enumerates specific actions (sync, list, activate, delete). This clearly differentiates from sibling tools like evm_address_history and utxo_address_history, which focus on querying history.

  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 the tool: to manage addresses for Address History APIs. It details each action and even gives pagination guidance. However, it does not explicitly state when not to use it or name alternatives, though siblings are contextually different.

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