Server Quality Checklist

Tool Scores

• cancel_executionC
  2.9/5.0
  Behavior2/5

  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 states the action ('Cancel') and return ('Success status'), but lacks critical details: whether cancellation is reversible, permission requirements, side effects (e.g., on related resources), or error handling. This is inadequate for a mutation tool with zero annotation coverage.

  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 appropriately concise and well-structured, with a clear purpose statement followed by brief sections for Args and Returns. Every sentence adds value, and there's no redundant information, though it could be slightly more front-loaded by integrating the return note into the main description.

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

  Completeness3/5

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

  Given the tool's complexity (a mutation with no annotations) and the presence of an output schema (which handles return values), the description is minimally complete. It covers the basic action and parameter, but gaps in behavioral transparency and usage guidelines make it insufficient for optimal agent operation, especially compared to siblings like 'execute_query'.

  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 description adds minimal semantics beyond the input schema: it explains that 'execution_id' refers to 'the execution ID of the running query,' which clarifies the parameter's purpose. However, with 0% schema description coverage and only one parameter, this provides basic context but doesn't fully compensate for the schema's lack of descriptions (e.g., format or source of the ID).

  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's purpose with a specific verb ('Cancel') and resource ('ongoing query execution'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'archive_query' or 'delete_table' which might also involve termination operations, preventing 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 Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., that an execution must be running), exclusions, or relationships to siblings like 'get_execution_status' for checking status before cancellation, leaving the agent to infer usage context.

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

• execute_queryC
  2.9/5.0
  Behavior2/5

  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 mentions the action ('Execute') and return value ('Execution details including execution_id'), but lacks critical information about side effects (e.g., does execution consume resources?), permissions required, rate limits, or what happens if the query fails. This is inadequate for a tool that likely performs server-side operations.

  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 (Args, Returns) and uses minimal sentences. However, the 'Args' section could be more integrated into the flow rather than listed separately, and some details feel slightly redundant (e.g., repeating 'query' in parameter names).

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

  Completeness3/5

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

  Given the complexity (3 parameters, no annotations, but has output schema), the description is moderately complete. It covers the basic purpose and parameters, and the output schema handles return values. However, it misses important context like error handling, execution timeouts, or how this interacts with sibling tools (e.g., 'get_execution_status'), leaving gaps for an agent to use it effectively.

  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 description lists all three parameters with brief explanations, which adds value since schema description coverage is 0%. However, it doesn't explain the format of 'query_parameters' (e.g., expected key-value structure) or practical implications of 'performance' tiers (e.g., cost or speed differences). The coverage is basic but compensates somewhat for the schema gap.

  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 action ('Execute a saved query') and the resource ('by its ID'), making the purpose immediately understandable. However, it doesn't explicitly distinguish this tool from sibling tools like 'execute_sql' or 'get_query_results', which could cause confusion about when to use each.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives like 'execute_sql' (for direct SQL execution) or 'get_query_results' (for retrieving results). It also doesn't mention prerequisites such as needing a saved query ID or when performance tiers matter.

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

• archive_queryB
  3.1/5.0
  Behavior2/5

  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 states the action ('archive') and effects ('uneditable and unexecutable'), which implies a mutation operation. However, it lacks details on permissions required, whether the action is reversible, error conditions (e.g., invalid query_id), or side effects (e.g., impact on related executions). For a mutation tool with zero annotation coverage, this is insufficient.

  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 appropriately sized, with a clear purpose statement followed by Args and Returns sections. Every sentence earns its place by explaining the action, parameter, and outcome. However, the 'Returns' section is somewhat redundant given the output schema, slightly reducing efficiency.

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

  Completeness3/5

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

  Given the tool's complexity (a mutation with one parameter) and the presence of an output schema (which covers return values), the description is partially complete. It explains the action and parameter semantics adequately but lacks behavioral details like error handling or reversibility. With no annotations and an output schema, it should provide more context on usage and constraints to be fully helpful.

  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 description adds meaningful context for the single parameter 'query_id' by specifying it as 'The unique identifier of the query to archive.' This clarifies its purpose beyond the schema's basic type (integer). With 0% schema description coverage and only one parameter, the description effectively compensates by providing essential semantic information, though it doesn't detail format constraints (e.g., valid range).

  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 verb ('archive') and resource ('query'), and specifies the outcome ('making it uneditable and unexecutable'). It distinguishes from siblings like 'delete_table' or 'update_query' by focusing on archival rather than deletion or modification. However, it doesn't explicitly differentiate from similar tools like 'make_query_private' or 'make_query_public', which also affect query accessibility.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing query), exclusions (e.g., cannot archive already archived queries), or comparisons to siblings like 'delete_table' (for removal) or 'make_query_private' (for access control). Usage is implied but not explicitly stated.

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

• insert_table_rowsB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. While it mentions the table must exist and shows an example, it doesn't address critical aspects like required permissions, whether the operation is idempotent, error handling for duplicate rows, or performance characteristics like batch size limits.

  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 with the core purpose, followed by clearly labeled sections for Args, Returns, and Example. Every sentence adds value with no redundancy, making it easy to scan and understand quickly.

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

  Completeness3/5

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

  For a mutation tool with 3 parameters, 0% schema coverage, and no annotations, the description provides basic operational context but lacks important details about permissions, constraints, and error scenarios. The presence of an output schema helps with return values, but behavioral aspects remain underspecified.

  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%, but the description provides meaningful context for all 3 parameters: it explains namespace and table_name identify the target, and rows must match column names. The example further clarifies row structure. This compensates somewhat but doesn't fully document data types, constraints, or validation rules.

  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 action ('Insert rows') and target resource ('into an existing table'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this from sibling tools like 'upload_csv' or 'create_table', which might handle similar data insertion scenarios.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives like 'upload_csv' or 'execute_sql'. It mentions the table must be 'existing' but doesn't clarify prerequisites, error conditions, or typical use cases compared to sibling tools.

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

• get_queryB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states this is a retrieval operation ('Retrieve details'), implying it's read-only, but doesn't specify permissions, rate limits, or error handling. The description adds minimal behavioral context beyond the basic action, leaving gaps in understanding how the tool behaves in practice.

  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 concise, using a clear main sentence followed by 'Args:' and 'Returns:' sections. Every sentence adds value: the purpose, parameter meaning, and return details. It's front-loaded with the core action, though the formatting could be slightly more integrated (e.g., avoiding separate sections if not standard).

  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 (1 parameter, no nested objects) and the presence of an output schema (which handles return value documentation), the description is reasonably complete. It covers the purpose, parameter semantics, and high-level return content. However, it lacks usage guidelines and behavioral details, which are minor gaps given the simple read-only nature.

  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 description adds meaningful semantics for the single parameter: 'query_id: The unique identifier of the query.' This clarifies that 'query_id' refers to a saved query's ID, not a query string or other identifier. With 0% schema description coverage, the description fully compensates by providing essential context that the schema lacks, making it clear what the parameter represents.

  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's purpose: 'Retrieve details about a saved query.' It uses a specific verb ('Retrieve') and resource ('saved query'), making the action clear. However, it doesn't explicitly differentiate from siblings like 'get_query_results' or 'get_execution_status', which also retrieve query-related information but focus on different aspects.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a saved query ID), exclusions, or comparisons to siblings like 'get_query_results' (which might return query execution results) or 'update_query' (which modifies queries). This leaves the agent to infer usage from context alone.

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

• get_execution_resultsB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that it retrieves results for a 'completed query execution,' implying read-only behavior, but doesn't cover critical aspects like authentication needs, rate limits, error handling, or what happens if the execution isn't complete. For a tool with zero annotation coverage, this is insufficient.

  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 with the core purpose, followed by clear sections for Args and Returns. Every sentence adds value: the first states the tool's function, and the subsequent bullet points efficiently document parameters and return values without redundancy. It's appropriately sized for the tool's complexity.

  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 moderate complexity (3 parameters, no annotations, but with an output schema), the description is fairly complete. It covers the purpose, parameters, and return values, and the output schema handles return details, reducing the need for extensive description. However, it lacks usage guidelines and behavioral context, which are minor gaps in an otherwise solid description.

  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 description adds significant value beyond the input schema, which has 0% description coverage. It explains the purpose of each parameter: 'execution_id' is for a completed query, 'limit' specifies maximum rows with default and max per page, and 'offset' is for pagination with a default. This compensates well for the schema's lack of descriptions, though it doesn't detail format constraints (e.g., execution_id format).

  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's purpose: 'Retrieve the results of a completed query execution.' It specifies the verb ('retrieve') and resource ('results of a completed query execution'), making the function unambiguous. However, it doesn't explicitly differentiate from siblings like 'get_query_results' or 'get_execution_results_csv', which would be needed for 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 Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., that the execution must be completed), compare it to siblings like 'get_execution_status' or 'get_execution_results_csv', or specify scenarios where it's preferred over similar tools. This leaves the agent without context for selection.

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

• create_tableB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool creates a table, implying a write operation, but doesn't cover critical aspects like required permissions, whether the operation is idempotent, error handling, or rate limits. The 'Returns' section mentions a confirmation but lacks details on format or potential errors, leaving significant gaps for a mutation tool.

  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 (description, args, returns, example) and front-loaded purpose. It's appropriately sized for a 4-parameter tool with complex nested data. However, the example is lengthy and could be slightly trimmed without losing clarity, and some redundancy exists (e.g., restating parameter names in the description).

  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 (mutation with 4 parameters, nested objects in 'columns', no annotations, but has output schema), the description is mostly complete. It covers all parameters in detail and includes an example, which is crucial for understanding the 'columns' structure. The output schema exists, so the description doesn't need to explain return values extensively, but it could benefit from more behavioral context (e.g., error cases).

  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 so effectively: it documents all 4 parameters (namespace, table_name, columns, is_public), provides detailed semantics for 'columns' (including nested structure with name, type, nullable, and data type enums), and clarifies defaults (nullable default True, is_public default false). This 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.

  Purpose4/5

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

  The description clearly states the tool's purpose: 'Create a new table with a defined schema.' This specifies the verb ('create') and resource ('table'), and the mention of 'defined schema' adds useful detail. However, it doesn't explicitly differentiate from sibling tools like 'upload_csv' (which might also create tables) or 'clear_table' (which modifies existing tables), keeping it from 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 Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'upload_csv' (which might create tables from CSV files) or 'create_query' (which might involve table creation indirectly), nor does it specify prerequisites or contexts for use. The example shows usage but doesn't explain when it's appropriate.

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

• make_query_privateB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It mentions 'restricting access to the owner' which implies a mutation with permission changes, but doesn't disclose behavioral traits like required permissions, reversibility, or effects on existing access. Significant gaps remain for a mutation tool.

  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 appropriately sized with a clear purpose statement followed by Args/Returns sections. It's front-loaded and efficient, though the Returns section could be more specific.

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

  Completeness3/5

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

  Given it's a mutation tool with no annotations, 0% schema coverage, but has an output schema, the description is moderately complete. It covers purpose and basic parameter semantics but lacks behavioral details and explicit usage guidelines.

  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%, but the description adds meaning by explaining 'query_id' as 'unique identifier of the query'. However, with only 1 parameter and no schema descriptions, it partially compensates but doesn't fully detail format or constraints.

  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 'make private' and the resource 'query', specifying it restricts access to the owner. It distinguishes from sibling 'make_query_public' by indicating opposite privacy action.

  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 when restricting query access, but doesn't explicitly state when to use vs alternatives like 'make_query_public' or provide prerequisites. Context is clear but lacks explicit guidance.

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

• get_execution_results_csvA
  3.5/5.0
  Behavior3/5

  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 adds some context beyond basic functionality: it mentions that results can be truncated if data exceeds 8GB when 'allow_partial_results' is true, which is useful for understanding limitations. However, it doesn't cover other potential behaviors like error handling, rate limits, or authentication needs, leaving gaps for a tool that retrieves data.

  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 clearly, followed by brief sections for 'Args' and 'Returns' that add necessary details without redundancy. Every sentence earns its place, making it efficient and easy to parse for an AI agent.

  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 moderate complexity (2 parameters, no annotations, but with an output schema), the description is fairly complete. It explains the purpose, parameters, and return value ('Query results as CSV string'), and the output schema likely covers return details, so it doesn't need to elaborate further. However, it could improve by addressing sibling tool distinctions or more behavioral aspects like error scenarios.

  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 description adds meaningful semantics beyond the input schema, which has 0% description coverage. It explains that 'execution_id' comes from a 'completed query', clarifying its source, and describes 'allow_partial_results' as allowing 'truncated results if data exceeds 8GB', providing crucial context on data limits. This compensates well for the low schema coverage, though it doesn't detail all possible edge cases.

  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's purpose: 'Retrieve query execution results in CSV format.' It specifies the verb ('retrieve'), resource ('query execution results'), and format ('CSV'), making it easy to understand. However, it doesn't explicitly differentiate from sibling tools like 'get_execution_results' or 'get_query_results_csv', which likely serve similar purposes, so it doesn't reach a score of 5.

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

  Usage Guidelines2/5

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

  The description provides minimal usage guidance. It mentions that 'execution_id' is from a 'completed query', implying a prerequisite, but doesn't specify when to use this tool versus alternatives like 'get_execution_results' or 'get_query_results_csv'. There's no explicit advice on when or when not to use it, leaving the agent to infer context from sibling tool names alone.

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

• get_query_results_csvA
  3.5/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden but lacks critical behavioral details. It mentions 'allow_partial_results' but doesn't explain what happens when data exceeds limits (e.g., truncation behavior, error handling). It also doesn't disclose authentication needs, rate limits, or whether this is a read-only operation (though 'Get' implies it).

  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 a clear purpose statement followed by organized parameter explanations and return information. Every sentence earns its place, though the 'Args:' and 'Returns:' sections could be slightly more integrated with the main description for better flow.

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

  Completeness3/5

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

  For a 7-parameter tool with no annotations but an output schema (implied by 'Returns: Query results as CSV string'), the description adequately covers parameters and purpose. However, it lacks behavioral context (e.g., error conditions, performance characteristics) that would be helpful given the tool's complexity and data manipulation capabilities.

  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?

  With 0% schema description coverage, the description fully compensates by providing clear explanations for all 7 parameters. Each parameter gets a concise definition that adds meaning beyond the schema (e.g., 'SQL ORDER BY expression' for sort_by, 'SQL WHERE clause' for filters), making this excellent for parameter understanding.

  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 latest results'), resource ('of a saved query'), and format ('in CSV format'), distinguishing it from siblings like 'get_query_results' (which presumably returns a different format) and 'get_execution_results_csv' (which works on executions rather than saved queries).

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives like 'get_query_results' or 'get_execution_results_csv'. It mentions 'latest results' but doesn't clarify prerequisites (e.g., whether the query must be saved or executed first) or exclusions.

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

• create_queryA
  3.8/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden. It mentions the tool 'creates and saves' a query, implying persistence and mutation, but doesn't disclose authentication requirements, rate limits, whether the operation is idempotent, or what happens on duplicate names. The example helps but doesn't cover behavioral traits comprehensively.

  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?

  Well-structured with clear sections (Args, Returns, Example) and front-loaded purpose statement. The parameter explanations are detailed but necessary given 0% schema coverage. Slightly verbose but each sentence adds value for 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 6 parameters with 0% schema coverage and no annotations, the description does an excellent job explaining parameters and providing an example. The output schema exists ('Returns: Created query details including query_id'), so return values don't need explanation. Minor gap in behavioral context for a mutation tool.

  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 provides detailed explanations for all 6 parameters, including syntax guidance for query_sql ('Use {{param_name}} for parameters'), default values, optional status, and nested structure for parameters field. This adds substantial meaning 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 clearly states the specific action ('Create and save a new query') and resource ('on Dune'), distinguishing it from siblings like update_query, execute_query, or get_query. It explicitly mentions saving, which differentiates it from temporary execution tools.

  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 creating persistent queries on Dune, but doesn't explicitly state when to use this versus alternatives like execute_sql (for one-time execution) or update_query (for modifications). No explicit exclusions or prerequisites are mentioned.

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

• make_query_publicA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It mentions the action ('make public') and outcome ('allowing broader access'), but lacks details on permissions needed, whether the change is reversible, rate limits, or error conditions. This is inadequate for a mutation tool with zero annotation coverage.

  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 front-loaded with the core purpose in the first sentence, followed by structured 'Args' and 'Returns' sections. It's efficient with minimal waste, though the 'Returns' section could be integrated more seamlessly.

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

  Completeness3/5

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

  Given the tool's complexity (mutation with privacy implications), lack of annotations, and presence of an output schema (which covers return values), the description is partially complete. It explains the action and parameter but misses behavioral details like authorization needs or side effects, leaving gaps for safe agent 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?

  The description adds meaningful context for the single parameter 'query_id' by explaining it's 'The unique identifier of the query,' which clarifies its purpose beyond the schema's type 'integer.' With 0% schema description coverage and only one parameter, this compensates well, though it doesn't specify format constraints (e.g., valid 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 clearly states the specific action ('Make a private query public') and the resource affected ('query'), distinguishing it from siblings like 'make_query_private' (opposite action) and 'update_query' (general modification). The verb 'make' and scope 'allowing broader access' provide precise 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 implies usage context by specifying 'private query' as the target, suggesting this tool is for changing privacy settings. However, it does not explicitly state when to use this versus alternatives like 'update_query' for other modifications or prerequisites (e.g., ownership requirements).

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

• clear_tableA
  3.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden. It discloses the destructive nature ('Remove all data') but lacks details on permissions needed, whether the action is reversible, rate limits, or error conditions. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.

  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 structured Args and Returns sections. Every sentence earns its place with no wasted words, making it highly efficient and well-organized.

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

  Completeness3/5

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

  Given the tool's complexity (destructive operation with 2 parameters) and no annotations, the description is minimally adequate. It covers purpose and parameters but lacks behavioral details. The presence of an output schema ('Returns: Clear confirmation') helps, but more context on safety and usage would improve completeness.

  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. It adds meaning by explaining that 'namespace' and 'table_name' identify the target table, though it doesn't specify format or constraints. Since there are only 2 parameters and the description clarifies their roles, it adequately 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 clearly states the specific action ('Remove all data from a table') and distinguishes it from sibling tools like 'delete_table' (which removes the entire table) by specifying 'while preserving its schema.' This provides precise verb+resource differentiation.

  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 by contrasting with schema preservation, suggesting it's for resetting data without structural changes. However, it doesn't explicitly state when to use this versus alternatives like 'delete_table' or 'insert_table_rows' for data management, nor does it mention prerequisites or exclusions.

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

• update_queryA
  4/5.0
  Behavior3/5

  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 the partial update behavior ('Only fields provided will be updated'), which is valuable. However, it doesn't mention critical behavioral traits like authentication requirements, error conditions (e.g., invalid query_id), rate limits, or whether the update is reversible. The return statement is generic ('Update confirmation') without detailing success/failure responses.

  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 a purpose statement, behavioral note, parameter list, and return statement. Every sentence adds value, and it's front-loaded with the core purpose. The parameter list is necessary given 0% schema coverage, but it could be slightly more concise by integrating some details into the schema.

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

  Completeness3/5

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

  Given the complexity (7 parameters, mutation operation, no annotations) and an output schema (which likely covers return values), the description is moderately complete. It explains parameters and partial update behavior but lacks context on authentication, error handling, and sibling tool differentiation. For a mutation tool with no annotations, more behavioral disclosure would be beneficial.

  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. It provides clear semantic explanations for all 7 parameters (e.g., 'query_id: The unique identifier of the query to update'), adding meaning beyond the bare schema types. However, it doesn't explain parameter interactions (e.g., that null values might be ignored) or constraints (e.g., query_sql syntax validation).

  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 action ('Update an existing saved query') with specific resources involved (saved query). It distinguishes this from sibling tools like 'create_query' (for new queries) and 'make_query_private/public' (which handle only privacy settings). The verb+resource combination is precise 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 context for when to use this tool: when updating existing saved queries. It distinguishes from 'create_query' (for new queries) by specifying 'existing saved query.' However, it doesn't explicitly state when NOT to use it (e.g., vs. 'make_query_private' for privacy-only changes) or mention prerequisites like authentication needs.

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

• delete_tableA
  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 of behavioral disclosure. It effectively communicates the destructive nature ('permanently delete', 'irreversible'), which is critical for a mutation tool. However, it lacks details on permissions, rate limits, or error conditions (e.g., what happens if the table doesn't exist), leaving some behavioral aspects uncovered.

  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 action and warning, followed by structured Arg/Return sections. Every sentence earns its place: the first states the purpose, the second warns, and the bullet points clarify parameters and output without redundancy. It is appropriately sized for a destructive operation.

  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 high complexity (destructive mutation), no annotations, and an output schema (implied by 'Returns'), the description does well by emphasizing irreversibility and confirming deletion. However, it could be more complete by addressing prerequisites (e.g., required permissions) or error handling, which are important for such a critical tool.

  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. It adds meaningful context by explaining that 'namespace' and 'table_name' identify the table to delete, which clarifies their roles beyond the bare schema. However, it does not provide format examples or constraints (e.g., naming rules), leaving some semantic gaps.

  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 ('permanently delete') and resource ('a table and all its data'), distinguishing it from siblings like 'clear_table' (which likely removes data but not the table structure) or 'archive_query' (which deals with queries rather than tables). The verb+resource combination is precise 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 context with the 'WARNING: This operation is irreversible!' statement, implying it should be used cautiously and not for reversible operations. However, it does not explicitly name alternatives (e.g., 'clear_table' for removing data without deleting the table) or specify when-not-to-use scenarios beyond the warning, which prevents a perfect score.

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

• upload_csvA
  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 full burden and does well by disclosing key behavioral traits: the 200MB file size limit, the destructive overwrite behavior for existing tables, and the confirmation return. It doesn't mention authentication requirements, rate limits, or error conditions, but provides substantial operational 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 perfectly structured: a clear purpose statement upfront, followed by important constraints, then organized parameter explanations with a practical example. Every sentence earns its place, with no redundant information. The formatting with sections enhances readability without being verbose.

  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 no annotations, 0% schema description coverage, but with output schema present, this description is remarkably complete. It covers purpose, constraints, parameters, return value, and provides an example. The output schema handles return structure details, so the description appropriately focuses on operational context. This is comprehensive for a data upload tool.

  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, the description compensates well by explaining all 4 parameters in the Args section: table_name accessibility pattern, data format requirements, description optionality, and is_private purpose. The example further clarifies data format. It doesn't specify character limits or validation rules, but provides meaningful semantic context for each 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 clearly states the specific action ('Upload CSV data') and resource ('create or overwrite a table in Dune'), distinguishing it from siblings like create_table (which likely creates empty tables) and insert_table_rows (which adds to existing tables). The verb 'upload' combined with the CSV format and Dune platform context provides precise 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 clear context about when to use this tool: for uploading CSV data to create new tables or overwrite existing ones. It implicitly distinguishes from siblings like create_table (no data upload) and insert_table_rows (append rather than overwrite), but doesn't explicitly name alternatives or specify when NOT to use this tool.

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

• execute_sqlA
  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 and does this well. It explains that the tool returns an execution_id for checking status/retrieving results, mentions performance tiers with defaults, and references external syntax documentation. It doesn't cover rate limits, authentication requirements, 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 well-structured and efficiently organized with clear sections (purpose, args, returns, examples). Every sentence adds value - no repetition or filler. The front-loaded purpose statement immediately communicates the tool's core function, making it easy for an agent to understand.

  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 (raw SQL execution), no annotations, and the presence of an output schema, the description provides excellent contextual completeness. It covers purpose, parameters with semantics, return value explanation, and practical examples. The output schema handles return value details, so the description appropriately focuses on operational context.

  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?

  Despite 0% schema description coverage, the description provides excellent parameter semantics. It clearly explains both parameters: 'sql' includes syntax reference and examples, and 'performance' explains the two tiers and default value. This fully compensates for the schema's lack of descriptions and adds meaningful context beyond basic type 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 clearly states the tool's purpose with specific verb ('Execute') and resource ('raw SQL query against Dune's data engine'), and distinguishes it from siblings by calling it 'the primary tool for running custom SQL queries on blockchain data.' This explicitly differentiates it from other query-related tools like execute_query or get_query_results.

  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 this tool ('primary tool for running custom SQL queries') and includes an example section showing typical use cases. However, it doesn't explicitly state when NOT to use it or mention specific alternatives among the many sibling tools, which prevents a perfect score.

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

• get_query_resultsA
  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 full burden and does well by disclosing key behavioral traits: it consumes credits, doesn't trigger new execution, returns cached results, and handles pagination/truncation. It doesn't mention rate limits, authentication needs, or error conditions, but covers the essential 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 efficiently structured with a clear purpose statement first, followed by behavioral context, then parameter explanations, and finally return format. Every sentence earns its place with no wasted words, and information is well-organized 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 tool's moderate complexity, no annotations, 0% schema coverage, but with an output schema present, the description is complete enough. It covers purpose, behavioral constraints, all parameter meanings, and mentions the return format, providing sufficient context for the 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?

  With 0% schema description coverage, the description fully compensates by explaining all 4 parameters' semantics: query_id as 'unique identifier', limit as 'maximum rows', offset for 'pagination', and allow_partial_results for allowing 'truncated results if data is too large'. This adds significant 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 clearly states the tool's purpose with specific verbs ('Get the latest results', 'retrieves cached results') and distinguishes it from siblings like execute_query by emphasizing it doesn't trigger new execution. It explicitly identifies the resource as 'saved query' results.

  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 this tool ('without re-executing', 'retrieves cached results from the most recent execution') and distinguishes it from execution tools. However, it doesn't explicitly mention when NOT to use it or name specific alternatives like get_execution_results for fresh results.

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

• get_execution_statusA
  4.7/5.0
  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 it's for polling (implying potential repeated calls), mentions the return includes state, queue position, and timing info, and implies it's a read operation. It doesn't specify error handling or rate limits, but covers key behavioral aspects.

  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 usage guidance and parameter/return details in a structured format. Every sentence adds value without redundancy, 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 moderate complexity, no annotations, and the presence of an output schema (which handles return values), the description is complete enough. It covers purpose, usage, parameter context, and high-level return info, aligning well with the structured data.

  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. It adds meaning by explaining that execution_id comes 'from execute_sql or execute_query,' clarifying the source and purpose beyond the schema's basic string type. However, it doesn't detail format or constraints.

  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 verb ('check') and resource ('status of a query execution'), distinguishing it from siblings like execute_query (which initiates execution) and get_execution_results (which retrieves results). It precisely defines what the tool does.

  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 this tool: 'to poll for completion after executing a query.' It also distinguishes from alternatives by not being for initiating queries (execute_sql/execute_query) or retrieving results (get_execution_results). This provides clear context and exclusions.

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