Server Quality Checklist

Tool Scores

• lint_sqlB
  3.2/5.0
  Behavior3/5

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

  Discloses a limitation (some errors like trailing commas undetected) which adds value beyond name. However, without annotations, it does not confirm read-only behavior or side effects, leaving some behavioral ambiguity.

  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?

  Two sentences plus a bullet-like Args/Returns. First sentence front-loads purpose, second adds a key caveat. No fluff, though integration of Args could be tighter.

  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?

  Explains return value format, which is helpful. But missing details like what constitutes a syntax error, handling of invalid inputs, or scope (e.g., only syntax, not semantics). Adequate but not comprehensive.

  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 coverage is 0%, so description must compensate. The Args section adds 'SQL query to analyze' for sql and 'Optional SQL dialect (e.g., 'mysql', 'postgres')' for dialect, providing examples. But sql parameter lacks details on input format or constraints.

  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 it lints SQL queries and returns syntax errors, with a specific verb 'Lint' and resource 'SQL query'. It distinguishes from siblings that handle references and transpilation, though not explicitly.

  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?

  No guidance on when to use vs alternatives. Only implies use for syntax checking, but no 'when not to use' or comparison with siblings like transpile_sql.

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

• get_all_column_referencesA
  3.5/5.0
  Behavior3/5

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

  With no annotations, description provides return format and mentions errors, but lacks details on side effects, performance, or prerequisites. It does note the dialect parameter influences 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?

  Extremely concise with clear structure: purpose sentence followed by structured Args and Returns. No unnecessary text, every sentence earns its place.

  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?

  Tool is simple with 2 parameters and no output schema. Description covers purpose, inputs, and output type. Lacks example output but sufficient for basic understanding.

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

  Parameters4/5

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

  Schema description coverage is 0%, but description adds meaning: 'sql: SQL statement to analyze' and 'dialect: Optional SQL dialect (e.g., 'mysql', 'postgres')', including an example for dialect.

  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?

  Description clearly states 'Extract column references from SQL statement with table context', which is a specific verb and resource. It implicitly distinguishes from sibling 'get_all_table_references' by focusing on columns, but does not explicitly contrast.

  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?

  No guidance on when to use this tool versus alternatives (e.g., get_all_table_references, lint_sql). Only states its purpose, not when-not or context.

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

• get_all_table_referencesA
  3.7/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It explains it extracts table/CTE names and returns JSON with specific attributes. However, it omits details about side effects (none expected), authentication needs, rate limits, or error handling. Adequate but not thorough.

  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 relatively concise, front-loading the purpose. The 'Args' and 'Returns' structure is clear. A minor improvement could be removing 'Args' and 'Returns' labels to be even more succinct.

  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, the description adequately explains return format (JSON with catalog, database, alias, and CTEs). It covers both input parameters. Missing details like error conditions or dialect validation, but overall sufficient for a simple extraction 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 0%, so description must add meaning. It describes 'sql' as 'SQL statement to analyze' and 'dialect' as 'Optional SQL dialect (e.g., 'mysql', 'postgres')'. This adds useful context beyond the schema's bare types and defaults.

  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 'Extract table and CTE names from SQL statement', with a specific verb and resource. It distinguishes from siblings like 'get_all_column_references' which extracts columns, making it clear what this 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 Guidelines2/5

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

  No explicit guidance on when to use this tool vs alternatives like 'lint_sql' or 'transpile_sql'. The description is purely declarative without usage context or exclusions.

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

• transpile_sqlA
  3.9/5.0
  Behavior3/5

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

  The description mentions it returns transpiled SQL or a syntax error, indicating a pure transformation. However, it does not disclose potential side effects, error handling details, or whether it modifies anything. With no annotations, this is minimally adequate.

  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 short lines with a structured Args/Returns section. No redundant words, front-loads the core purpose.

  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 simplicity (3 string params, no output schema), the description covers the purpose, parameters, and return value adequately. No gaps for this complexity level.

  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 docstring explains each parameter (sql, read_dialect, write_dialect) with brief descriptions, compensating for the 0% schema description coverage. The meaning is clear but could include dialect format or examples.

  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 first line clearly states it transpiles a SQL statement to another dialect, specifying the verb (transpile) and resource (SQL dialect conversion). It is distinct from siblings like lint_sql and get_all_table_references.

  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?

  No guidance on when to use this tool vs alternatives (e.g., lint_sql for validation). No mention of prerequisites or conditions that make this tool preferable.

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