Server Quality Checklist

Tool Scores

• list_connectionsA
  4/5.0
  Behavior4/5

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

  Discloses password redaction from URLs and return format (JSON array). Without annotations, covers key behavioral details. Could mention if connections require active status or any side effects.

  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, no redundancy, front-loaded with core action. Every sentence provides value.

  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 simple tool with one parameter and no output schema, description is fairly complete: purpose, return type, key behavior. Could clarify contents of 'connection configs' but adequate.

  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 100% so description adds only marginal context (redaction note). Description does not significantly enhance understanding beyond 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?

  Clearly states action (list) and resource (configured database connections), with added detail about permission (readonly). Distinguishes from sibling tools like get_schema, read_sql, write_sql by focusing on connection listing.

  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?

  Implied usage (when you need to see available connections), but no explicit guidance on when to prefer this over 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.

• read_sqlA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description step up by declaring the tool is read-only (non-destructive) and specifying the return format (JSON array of rows). However, it lacks details on authentication requirements, error handling, or SQL dialect limitations.

  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 highly concise with two sentences: the first states purpose and examples, the second states the return format. No wasted words and 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?

  For a simple tool with two parameters and no output schema, the description adequately covers purpose, read-only constraint, and return format. It could be improved by including error behavior or SQL dialect alerts, but overall 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 coverage is 100% as both parameters have detailed descriptions. The description adds no extra meaning beyond the schema, so it meets the baseline of 3.

  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 read-only SQL queries, specifies allowed examples (SELECT/SHOW/PRAGMA), and distinguishes itself from siblings like write_sql, get_schema, and list_connections.

  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 read operations via '只读' but does not explicitly state when to use this tool versus alternatives like write_sql for writes or get_schema for schema retrieval.

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

• get_schemaA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the behavioral burden. It reveals output format (Markdown) and conditional behavior, but does not disclose potential side effects (none expected), prerequisite validity of connection_name, or error handling for invalid table_names. The description adequately conveys read-only nature but lacks edge-case details.

  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 concise sentences front-load the core purpose and then detail the parameter-driven behavior. No redundant words or unnecessary details. Every sentence provides essential information.

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

  Completeness4/5

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

  Given the tool's simplicity (2 params, no output schema), the description covers purpose, parameter effect, and output format adequately. While it does not specify the exact Markdown structure or error messages, it is sufficient for an agent to understand and invoke correctly. A brief example or note on connectivity would enhance 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 coverage is 100% with good parameter descriptions. The description adds value beyond the schema by explaining how the optional parameter changes output (summary vs column details). This behavioral mapping helps the agent understand the impact of omitting or including table_names.

  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 it retrieves the database schema in Markdown format. It distinguishes default behavior (all tables summary) from optional behavior (specific table details with table_names). This verb+resource+scope specification effectively separates it from siblings like list_connections or read_sql.

  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 explains when to use each parameter variant: omit table_names for summary, provide for column details. However, it does not explicitly state when to use this tool versus siblings (e.g., for schema inspection vs data queries), though the purpose is clear. Slight room for improvement in exclusion guidance.

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

• write_sqlA
  4.2/5.0
  Behavior3/5

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

  No annotations exist, so description carries full burden. It discloses write operation and return format but lacks details on side effects or error states.

  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 convey all necessary information without redundancy. Front-loaded and efficient.

  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 return format is specified. The readonly condition is mentioned, but error handling and transaction behavior are omitted. Acceptable for a simple 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 covers both parameters with descriptions. The description adds context on allowed SQL types (write operations), slightly exceeding 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 write SQL (INSERT/UPDATE/DELETE/DDL) and distinguishes it from sibling tools like read_sql.

  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 specifies a precondition (readonly=false) and return format, but does not explicitly compare to alternatives or state 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.