Server Quality Checklist

Tool Scores

• describe_tableB
  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. However, it doesn't mention whether this is a read-only operation, whether it requires specific permissions, what happens if the table doesn't exist, or what the return format looks like beyond 'columns and types'. For a schema-inspection tool the behavioral surface is fairly simple, but there's still no error-handling or permission context disclosed.

  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 a single clean sentence with zero wasted words. It front-loads the core purpose clearly. It's appropriately concise, though it could use its brevity budget to add behavioral or parameter detail.

  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 single-parameter introspection tool with an output schema present, the description tells the agent essentially what it needs: inspect the columns and types of a table. The output schema presumably documents the return shape. Given the low complexity, the description is near-complete, though adding guidance differentiating from run_query would fully close the loop.

  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 for the single parameter. The description does mention 'a given table' linking to table_name, but it doesn't specify constraints like whether it must be an existing table, case-sensitivity, or schema-qualified naming format. With only one simple parameter, the description adds modest value over the 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 'Show the columns and their types for a given table' clearly states the verb (show), resource (columns/types of a table), and the singular parameter. It distinguishes reasonably from siblings (list_tables lists tables, run_query executes queries), though it doesn't explicitly call out the differentiation.

  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 context (inspecting table schema before querying) but provides no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives like list_tables for discovering available tables or run_query for custom inspection.

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

• run_queryB
  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 does state read-only and that it returns results, but doesn't document behaviors like whether multiple statements are allowed, statement timeouts, row-count limits, or error behavior for invalid SQL. With zero annotation coverage, this is a notable 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?

  A single sentence, zero wasted words. Every element earns its place: the action, the nature (read-only), the resource (business database), and the output (returns results). Optimal length for the information conveyed.

  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?

  There is an output schema present, so return-value documentation isn't required from the description. With 1 simple parameter and clear sibling context, the core task is adequately described. However, given zero annotations, some additional guidance about error handling or result-set behavior (e.g., max rows) would improve completeness for a database query tool.

  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?

  There's only 1 parameter (sql) with 0% schema description coverage. The description mentions 'SQL SELECT query' which tells the agent the sql parameter should contain a SELECT statement, adding some value over the bare schema. However, it doesn't clarify format nuances (e.g., semicolons, parameterization, quoting) beyond what a user would naturally infer.

  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 (run), resource (SQL SELECT query), and scope (read-only, business database). It distinguishes from siblings by specifying it's a SELECT query that returns results, while siblings list/describe tables. However, it could more explicitly note it differs from the schema-related 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 'read-only' qualifier gives some usage guidance (safe to call, won't mutate data), and returning "results" implies it's for data retrieval. However, it doesn't explicitly state when to use this vs describe_table or list_tables, nor does it disclose any limits (large queries, timeouts, multi-statement restrictions).

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

• list_tablesA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries some burden. 'List all tables' conveys a non-destructive read operation, which aligns with the sibling context. However, it doesn't disclose what information is returned per table (just names? schemas? row counts?), pagination limits, or whether permissions are needed. With no annotations at all, slightly more disclosure would be valuable, but the safe-read nature is reasonably conveyed.

  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?

  A single, complete sentence with zero waste. Could arguably be considered slightly under-specified, but for a zero-parameter discovery tool, this length is appropriate and front-loaded with the essential verb-resource structure.

  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 0 parameters, an output schema, and a simple list-and-return purpose, the description is adequately complete. It explains the key behavior (returns all table names) and the schema and output schema handle the rest. A bit more detail on what fields are returned per table might elevate it, but as-is it's sufficient for the tool's simplicity.

  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 tool has 0 parameters, and schema coverage is 100% (trivially, since there are no properties). The baseline for 0 parameters is 4 per the rubric. The description doesn't need to add parameter meaning since none exist, and there's no ambiguity to resolve.

  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 the action (list all tables) and resource (business database). While it doesn't explicitly distinguish from siblings, the tool names are self-explanatory enough that list_tables vs describe_table vs run_query are obviously distinct. Could note specifics about what 'all tables' includes (e.g., system tables, schemas) but the core purpose is clear.

  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 it's the discovery entry point (list tables before describing or querying), and the sibling names naturally establish context. However, there's no explicit when-to-use guidance or mention that this is the precursor to using describe_table or run_query. The guidance is implied by the tool name and sibling set rather than stated.

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