Server Quality Checklist

Tool Scores

• pg_stat_statementsA
  3.8/5.0
  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 explains that query text uses $1/$2 placeholders (normalization), notes the extension requirement with deployment-specific details, and outlines the return format. It is transparent about the read-only nature and typical usage, but does not explicitly declare non-destructiveness.

  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 concise (about 4 sentences), front-loaded with the purpose, and well-structured with a clear breakdown of return format, normalization behavior, and extension requirements. A minor quibble is the inline return schema which adds some verbosity, but overall it 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?

  Given the complexity of a database performance tool and the presence of an output schema (not shown but referenced), the description covers purpose, return format, normalization, and extension prerequisites. It lacks parameter explanation but the input schema covers that. Overall it is complete enough for an agent to understand the tool's role.

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

  Parameters1/5

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

  The description does not explain the parameters (limit and project_id) at all. Given the schema description coverage is 0%, the description should compensate, but it fails to add any meaning beyond the schema's own parameter descriptions. The agent must infer the limit from 'top N' and is left uninformed about project_id.

  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 'Return the top N most expensive queries from pg_stat_statements,' specifying a specific verb and resource. It further positions this as the 'best starting point for a performance audit,' which distinguishes it from sibling tools like execute_postgres or explain_postgres.

  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 clear context for use ('Best starting point for a performance audit') and implies it is for identifying costly query patterns. It does not explicitly state when not to use it or name alternatives, but the context and sibling tool names make the intended usage clear.

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

• describe_postgres_schemaA
  3.9/5.0
  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 describes the return structure and warns about large schemas, but does not explicitly state read-only nature, required permissions, or error handling. The word 'Inspect' implies read-only, but more explicit disclosure would improve transparency.

  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 concise (about 100 words) and front-loaded with purpose. It uses bullet-style formatting for the return structure. There is no unnecessary verbosity, but it could be slightly tighter by condensing the usage advice.

  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 and the presence of an output schema, the description covers key aspects: purpose, when to use, return format, and large schema handling. Minor gaps include not specifying behavior for nonexistent schemas or error conditions.

  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 high (both parameters have descriptions in the schema), so baseline is 3. The tool description does not mention parameters or provide additional semantics beyond what the schema already offers.

  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 'Inspect a PostgreSQL schema and return its full structure as JSON'. It differentiates from sibling tools like execute_postgres (execution), explain_postgres (query plan), list_projects (project listing), and pg_stat_statements (statistics), all of which have distinct purposes.

  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?

  Explicitly advises 'Call this before writing any query, JOIN, or EXPLAIN — it gives you exact table/column names and indexes so you don't guess'. It also recommends filtering client-side for large schemas, though it doesn't explicitly state when not to use or list alternatives.

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

• list_projectsA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses the return type (JSON object) and data source (databases.json), listing fields like 'default_project' and 'projects'. It does not mention authorization or side effects, but for a read-only listing tool, this level of transparency is 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?

  The description is concise, with three short segments: purpose, usage advice, and return format. It front-loads the key action and resource, and every sentence adds value without redundancy.

  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 zero parameters and an output schema described inline, the description is complete. It fully explains the tool's behavior, when to call it, and the structure of results, leaving no ambiguity for an AI agent.

  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 no parameters, and schema description coverage is 100% (empty schema). The description adds context about the returned structure, which enhances understanding beyond the schema, earning a baseline score of 4.

  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 lists all configured database projects and their access modes, using specific verb 'list' and resource 'database projects'. It distinguishes itself from sibling tools like 'execute_postgres' or 'describe_postgres_schema' which target different operations.

  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 advises 'Call this first when you don't know which project_id to use', providing a clear usage scenario. However, it does not mention when not to use it or suggest alternatives, but given the context, this guidance is sufficient.

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

• execute_postgresA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses key behaviors: mode enforcement (readonly blocks writes), return format with row_count, type casting for non-serialisable types, and the indicator that row_count equal to LIMIT suggests more rows. No contradictions.

  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?

  Concise and well-structured: purpose, return format, mode behavior, prerequisite call, and a caution about LIMIT. Every sentence adds value and the most critical info is front-loaded.

  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?

  Covers prerequisites, mode details, common pitfalls (LIMIT), and return format. With an output schema present (context signal), description does not need to explain return values further. No gaps identified.

  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?

  Input schema already provides parameter descriptions (sql and project_id). The description adds context about mode behavior affecting the sql parameter and suggests LIMIT usage, but does not elaborate on parameter syntax or format beyond the schema. Given low schema description coverage (0%), it compensates partially but not fully.

  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 the tool executes SQL queries on a PostgreSQL database and returns rows as JSON. Distinguishes from siblings like 'describe_postgres_schema' and 'explain_postgres' by focusing on execution rather than schema inspection or query planning.

  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?

  Includes explicit guidance: call 'describe_postgres_schema' first, explains mode behavior (readonly vs readwrite) with conditions, and advises adding LIMIT for unfamiliar tables. Effectively helps agents decide when and how to use this tool vs alternatives.

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

• explain_postgresA
  4.9/5.0
  Behavior5/5

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

  Discloses that the query executes to collect real timing, results are discarded, a statement timeout prevents runaway, and write queries are blocked. With no annotations, the description fully covers behavioral traits.

  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 concise, front-loaded with the main action, followed by execution details, return format, and usage guidance. Every sentence adds value with no wasted words.

  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?

  The description covers what the tool does, how it works (including execution and timeout), return format, when to use, and what is blocked. With an output schema present (not shown but referenced), the return information is sufficient. All necessary context for an agent to use the tool correctly is provided.

  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 already provides detailed parameter descriptions. The tool description adds context like the automatic prepending of EXPLAIN and the 'write queries blocked' constraint, but does not repeat parameter definitions. Given schema coverage appears to be limited (per context signals), the description could have added more direct parameter guidance, but it is adequate.

  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 it runs EXPLAIN (ANALYZE, BUFFERS, FORMAT JSON) on a query and returns the plan. Distinguishes from sibling tools like execute_postgres (which runs queries) and describe_postgres_schema (which describes schema).

  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?

  Explicitly advises using this tool before slow/unfamiliar queries on large tables, and to check describe_postgres_schema first for indexes. Also states write queries are blocked, guiding the agent away from using it for writes.

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