Server Quality Checklist

Tool Scores

• get_schema_infoB
  3.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must disclose behavioral traits. It does state that the tool returns column metadata and accepts database.table notation, which is a useful behavioral detail. However, it does not explicitly confirm the tool is read-only, nor does it explain error behavior for nonexistent tables or other 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 two sentences, with the first sentence delivering the core purpose and the second adding a specific syntax detail. There is no fluff or redundancy; every sentence contributes value.

  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 tool is simple with one parameter and an existing output schema, so the description need not enumerate return values. It covers the basic purpose and a key syntax detail, but lacks explicit usage guidance to distinguish from sibling tools and does not address error handling or assumptions. This is adequate but minimal for a complete picture.

  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 only defines table_name as a string with no description, and schema coverage is 0%. The description adds meaningful context by specifying that database.table notation is accepted for cross-database lookups, which goes beyond the bare schema parameter. This compensates well for the lack of schema documentation.

  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 that the tool returns column metadata for a table, listing specific attributes (name, type, nullability, key, default). It uses a specific verb ('Return') and identifies the resource ('column metadata' for a table), but does not explicitly differentiate it from sibling tools like execute_sql or get_table_sample.

  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 a usage tip about database.table notation for cross-database lookups, but it gives no guidance on when to use this tool compared to alternatives. There is no mention of execute_sql or get_table_sample, nor any scenarios that would prefer schema inspection over those siblings.

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

• get_table_sampleA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It adds the useful constraint of max 20 rows and cross-database notation, but does not state whether the operation is read-only, how the sample is selected (e.g., random vs first rows), or any error behavior. This is adequate for a simple fetch but leaves 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 two sentences, with the main purpose front-loaded and no filler. Every phrase adds value, and it remains concise while conveying the essential behavior.

  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 simplicity and the presence of an output schema, the description covers the core functionality. It misses key context such as usage guidance vs siblings, the read-only nature, and semantics of the limit parameter. Completeness is adequate but not thorough.

  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%, so the description must compensate. It adds meaning to table_name by noting database.table notation, and implies a limit parameter by stating max 20. However, it does not explicitly explain the limit parameter's role or default, so the compensation is partial.

  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 fetches a representative sample of rows with a max of 20 from a table, distinguishing it from the sibling tools execute_sql and get_schema_info. The verb 'fetch' and resource 'sample from a table' are specific 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 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 versus the siblings. It does not mention that execute_sql is for arbitrary queries or that get_schema_info is for metadata. The only usage hint is the database.table notation, which is a parameter detail, not a when-to-use instruction.

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

• execute_sqlA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the safety disclosure burden. It clearly states 'read-only', which is a critical behavioral trait, and also discloses the return format (rows as JSON) and the single-statement limitation. This is strong transparency, though it does not cover potential edge cases like query timeouts or result 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 three concise sentences, each adding essential information: what it does, the return format, and a key constraint. No filler or repetition. It is well-structured and front-loaded with the primary purpose.

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

  Completeness4/5

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

  For a simple tool with one parameter and an output schema present, the description covers the core behavior: allowed query types, read-only nature, return format, and single-statement restriction. It does not explicitly contrast with sibling tools, but the allowed statement list provides sufficient context for an agent to select it appropriately.

  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 the description must compensate. The description implies the 'query' parameter contains the SQL text and constrains it to the allowed statement types. However, it does not provide examples or elaborate on parameter syntax, leaving some room for interpretation. The parameter name itself is self-explanatory, but the description adds only partial value 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?

  The description clearly states the tool executes SQL queries with a specific set of read-only statement types (SELECT / SHOW / DESCRIBE / EXPLAIN / WITH). This distinguishes it from sibling tools like get_schema_info and get_table_sample, which likely provide metadata and sample data rather than arbitrary 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 provides explicit allowed statement types and the 'single statements only' constraint, which helps the agent decide when to use this tool. While it does not mention alternatives by name, the listing of allowed query types implies when it is appropriate and excludes mutations and multi-statement queries.

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