Server Quality Checklist

Tool Scores

• queryTableA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full disclosure burden. It adds useful context about filter passthrough to BaseQL and the case-sensitivity nuance ("Exact matches are case-sensitive unless you use advanced operators in _filter"). However, it does not disclose the response format or whether pagination metadata is returned, and the read-only safety profile is only implied by the verb "Query".

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

  Conciseness5/5

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

  The description is three efficient sentences: purpose, usage positioning, and filter/case-sensitivity caveat. It is front-loaded with the core operation and every sentence earns its place with no redundancy.

  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?

  The input schema richly covers all parameters, but with no output schema, the description should clarify what the tool returns (records shape, pagination metadata, total counts). It does not. Additionally, the sibling "query" is ambiguous and the description never clarifies when one would use "query" instead of "queryTable".

  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% and each of the 6 parameters has a detailed description. The description adds only marginal value for filter (passthrough note and the "unless advanced operators" caveat) while the schema already documents operators, examples, and case-sensitivity more thoroughly. No new meaning is added for tableName, sort, limit, offset, or fields.

  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 a specific verb+resource+scope: "Query data from a table with filtering, sorting, and pagination." The phrase "Use this for most data retrieval needs" positions it against siblings, but it does not explicitly differentiate from the similarly named sibling "query", leaving some ambiguity.

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

  Usage Guidelines4/5

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

  "Use this for most data retrieval needs" gives clear context that this is the go-to retrieval tool. It does not name exclusions or explicitly direct agents to alternatives like searchTable or getFieldOptions for specialized cases, but the guidance is reasonably clear.

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

• getTableSchemaA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of disclosure. It indicates a read-only operation ('Get') and specifies the type of information returned, but it does not explicitly state that no data is modified or disclose any permissions, rate limits, or error behavior. For a schema lookup tool, this is adequate but not deeply transparent.

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

  Conciseness5/5

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

  Three sentences, each contributing a distinct purpose: the first states the operation, the second provides usage context, and the third emphasizes importance. No redundancy or padding.

  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 tool with one parameter and no output schema, the description provides enough to understand the purpose and when to use it. It mentions the kind of details returned and references other tools (via param schema). It could explicitly describe the output format, but given its simplicity, it is largely complete.

  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 tableName parameter. The description does not add meaning beyond the schema; it only reinforces the usage context already present in the parameter description.

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

  Purpose5/5

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

  The description uses a specific verb 'Get' with the resource 'detailed schema information for a specific table' and enumerates the content (field names, types, relationships). It clearly distinguishes from siblings like listTables (listing tables) and query/queryTable (querying data).

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

  Usage Guidelines4/5

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

  The description explicitly states when to use the tool: 'Use this to understand table structure before querying or to identify available fields for filtering/sorting.' It also mentions 'Essential for building correct GraphQL queries.' This gives clear context, though it doesn't explicitly name alternative tools or exclusions. The param schema adds 'use listTables first.'

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

• getFieldOptionsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses a key behavioral trait: 'Only shows values currently in use - empty options won't appear.' It also notes the return of unique values with counts, providing context beyond structured fields.

  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 three concise sentences, front-loaded with the primary purpose and supported by a behavior caveat. No redundant or filler content.

  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?

  Despite having no output schema and no annotations, the description covers purpose, usage, return shape (unique values with counts), and a critical behavioral note. It lacks explicit mention of read-only nature or sampling limitations, but these are implied by 'analyzing existing data' and the sampleSize parameter.

  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 all parameters documented. The description adds some semantic context (e.g., 'select/dropdown fields') but does not significantly enhance beyond what the schema already provides.

  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 function: 'Discover possible values for select fields (dropdowns) by analyzing existing data.' This is specific and distinguishes it from siblings like getTableSchema (schema) and query (data 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?

  Provides explicit use cases: 'Use this to see what values are actually being used in a field before filtering or to understand data patterns.' This gives clear context for when to use, though it does not explicitly mention alternatives or when not to use.

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

• searchTableA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that matching is exact, case-sensitive, and limited to string fields, which is key behavioral info. However, it omits return format, pagination behavior, or error handling, leaving some transparency 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?

  Two sentences total; the first states the core function, the second clarifies limitations and unsupported cases. No redundancy, perfectly front-loaded.

  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 no output schema and no annotations, the description covers purpose, limitations, and parameter usage adequately. It doesn't need to explain return values since there's no output schema, but it could mention behavior for missing results or defaults.

  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 covers all 4 params with descriptions, so baseline is 3. Description adds meaning by instructing 'use fields to control which' and restricting to string fields, providing extra semantics 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?

  Description uses 'Search' with specific verb+resource: 'Search for records by exact, case-sensitive matches on string fields.' It clearly distinguishes from full-text search by explicitly stating 'This is not full-text search.' This sets it apart from sibling tools like query or queryTable.

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

  Usage Guidelines4/5

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

  Provides clear context: use for exact, case-sensitive matches, and explicitly excludes unsupported case-insensitive or partial matching. It doesn't name alternative tools but clarifies the boundary with 'BaseQL does not support it directly,' giving enough guidance for an agent.

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

• queryA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It adds valuable behavioral context: BaseQL uses Float instead of Int, '_page_size/_page' for pagination, and unquoted keys in filters. This goes beyond a generic 'query' description, though it does not specify read-only or potential mutation behavior, which is a minor gap.

  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 three concise sentences that front-load the purpose, then provide usage guidance and key conventions. Every sentence earns its place with no redundant or filler content.

  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 complex custom query tool with no output schema, the description and parameter schema together cover purpose, when to use, syntax examples, pagination, and linked records. It lacks explicit mention of read-only vs. mutation capabilities and does not explain error handling, but overall it is fairly complete for a query 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 coverage is 100%, so baseline is 3. The description adds meaning beyond schema by explaining BaseQL conventions (Float, pagination, filter syntax) that directly affect how to construct the 'query' parameter. This contextual guidance enhances the parameter descriptions already present 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 tool executes custom GraphQL queries against BaseQL, and directly distinguishes it from siblings by mentioning 'complex queries, joins across tables' and 'when other tools don't meet your needs.' This is a specific verb+resource with explicit 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?

  It provides clear when-to-use guidance: 'Use this for complex queries, joins across tables, or when other tools don't meet your needs.' It does not explicitly name alternative tools, but the sibling list is present and the phrase 'other tools' implies exclusion. The syntax tips further guide usage.

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

• listTablesA
  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 the full burden of behavioral disclosure. It explicitly states the return value ('Returns table names and descriptions') and implies a read-only, non-destructive operation. It doesn't discuss error conditions or rate limits, but for a simple listing tool, the key behavioral traits are covered.

  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 two sentences, front-loaded with the core action, and every clause adds value. It avoids redundancy and is highly scannable.

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

  Completeness5/5

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

  For a simple list tool with no annotations, no output schema, and no parameters, the description is remarkably complete. It states the purpose, provides usage workflow, and describes the return value, giving an agent everything needed to invoke 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 zero parameters, and the description correctly adds no parameter information. Per the rubric, a baseline of 4 applies when there are 0 parameters, and the description doesn't need to compensate.

  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 function: 'List all available tables' in the BaseQL endpoint. It uses a specific verb ('List') and resource ('tables'), and explicitly distinguishes itself from the sibling tool getTableSchema by positioning itself as the first step in discovery.

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

  Usage Guidelines5/5

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

  The description provides explicit usage guidance: 'Use this first to discover what data is available, then use getTableSchema to understand specific table structures.' This clearly indicates when to use this tool and how it fits into a workflow with an alternative.

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