Server Quality Checklist

Tool Scores

• analyze_indexesA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare read-only and non-destructive, so the description adds extra value by disclosing that the data source resets with the server and that exclusion rules apply. This behavior is not visible in annotations and is important for interpretation.

  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 sentences, each earning its place: findings, the reset caveat, and the exclusion rationale. It is front-loaded with the most important output information and has no filler.

  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?

  The description covers the key findings, data freshness caveat, and exclusions, which is fairly complete for a read-only analysis tool. It lacks a description of the return format and does not explain the 'schema' parameter, but overall it gives sufficient context for correct use.

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

  Parameters2/5

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

  The description does not mention either parameter. Schema coverage is only 50%, with 'database' described and 'schema' having only a default and no description, leaving the semantics of the 'schema' parameter unclear. The tool description should compensate for this gap but does not.

  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 enumerates the tool's outputs (unused indexes, duplicates, profitable sequential scans), which identifies it as an index analysis tool. It does not explicitly use a verb like 'analyze' or 'list', and it doesn't directly contrast with sibling tools, but the scope is unambiguous.

  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 important timing guidance: counters come from pg_stat_* and reset with server restart, so they should be read after real traffic. It also explains why primary-key and unique indexes are excluded, which helps the agent know when to trust results. It doesn't mention alternatives explicitly, but the context is sufficient.

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

• list_schemasA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by noting that PostgreSQL's own catalogs are excluded, which is valuable beyond the annotations. However, it does not describe the return format or other 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?

  The description is two concise sentences, both of which add value: the first states what the tool does and its scope, the second provides usage context. No unnecessary words or repetition.

  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?

  For a simple list tool with a single optional parameter, no output schema, and comprehensive annotations, the description is complete. It tells the agent what the tool does, what it excludes, and when to use it, which is sufficient for effective selection and invocation.

  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 100% for the single optional 'database' parameter, so the schema fully documents the parameter. The description does not add any additional meaning about the parameter, so the baseline score of 3 is appropriate.

  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 schemas in the database and explicitly excludes PostgreSQL's own catalogs, which distinguishes it from sibling tools like list_tables and describe_table. The verb 'list' is specific and the resource is well-defined.

  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 phrase 'Start here when you do not know the layout yet' provides clear contextual guidance for when to use the tool. It does not explicitly mention alternatives or exclusions, but for a simple discovery tool this is sufficient.

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

• list_tablesA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds valuable context: it includes views and materialized views, returns comments, and filters by the connected role's read permissions. This goes beyond the annotations without contradicting them.

  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 a single, front-loaded sentence with no filler. Every phrase adds meaning: object types, scope, comments, and access control.

  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 read-only list operation with annotations providing safety context, the description covers the key aspects: object types, scope, comments, and permission filtering. There is no output schema, but the return contents are sufficiently implied. It could mention ordering or limit behavior, but that is not critical for this tool.

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

  Parameters2/5

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

  Schema description coverage is only 50% because the 'schema' parameter lacks a description. The tool-level description mentions 'in one schema' but does not clarify the format or accepted values for the schema parameter. The 'database' parameter is well described in the schema, but the description does not compensate for the missing schema parameter details.

  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 specifies the verb 'list' and the resource (tables, views, materialized views) within a single schema, and includes comments. This distinguishes it from sibling tools like list_schemas and describe_table, which serve different 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?

  The description implies use when you need to enumerate objects within a schema and indicates the scope ('in one schema'). It does not explicitly exclude alternatives, but the context is clear enough for an agent to distinguish from list_schemas or describe_table.

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

• describe_tableA
  4.2/5.0
  Behavior5/5

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

  Annotations already declare read-only, idempotent, and non-destructive. The description adds crucial behavioral context: null 'description' means undocumented, not unused, preventing a common analytical error. This goes beyond the annotations to clarify interpretation of results.

  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 long. The first sentence efficiently lists the returned metadata categories, and the second adds a high-value clarification about null descriptions. Every word earns its place with no 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?

  For a simple describe tool, the description covers the return contents (columns, types, nullability, defaults, PK, comments) and an important edge case (null comment semantics). Annotations handle safety, and no output schema exists, so the description fully carries the explanatory burden.

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

  Parameters2/5

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

  Schema description coverage is only 33%, with only 'database' having a description. The tool description does not explain the semantics of 'schema' or 'table' parameters, nor does it clarify that two are required and one optional. Parameter meaning relies entirely on names, which is inadequate given the low schema coverage.

  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 specifies the tool returns column metadata (names, types, nullability, defaults, PK, comments) for one table. This distinguishes it from sibling tools like list_tables and list_schemas, which focus on listing rather than describing a single table's structure.

  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 use for inspecting a table's schema but provides no explicit 'when to use' or named alternatives. It gives context about what information is returned, which hints at suitable scenarios, but lacks exclusions or comparisons to sibling tools.

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

• top_queriesA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds a key behavioral trait: it requires the pg_stat_statements extension and will return instructions to enable it if absent. It also implies the output contains statement text suitable for explain_query. This adds meaningful transparency beyond the annotations.

  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 sentences, tightly packed with purpose, prerequisites, and a cross-reference to explain_query. It front-loads the primary action and avoids unnecessary elaboration. 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?

  Given the simplicity of the tool (2 params, no output schema), the description covers the essential aspects: what it does, the extension dependency, and a pointer to the next step. It doesn't mention ordering direction (descending) or output limit behavior, but these are reasonably inferred. It is nearly complete for a read-only listing 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?

  The schema provides descriptions for only one of two parameters (database) and the limit parameter has constraints but no description. The tool description does not mention parameters at all. With 50% schema coverage, the description should compensate, but it doesn't. The limit parameter is self-explanatory from its name and constraints, so a mid-score is appropriate.

  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 identifies the statements costing the most, ranked by total execution time server-wide. It distinguishes from siblings by specifying the resource (statements) and the metric (total execution time), and it contrasts with explain_query which is for plans.

  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 usage context: use to find top expensive statements, and then take the result to explain_query for the plan. It also notes the extension requirement and that the tool will explain how to enable it if missing. However, it doesn't explicitly state when not to use this tool versus other query tools, so it gets a 4 rather than 5.

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

• queryA
  4.3/5.0
  Behavior5/5

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

  The description goes well beyond the annotations by disclosing that writes/DDL/admin functions are refused, the default row limit of 1000, the maximum of 10000, the truncated flag, offset paging, and the need for ORDER BY to ensure stable pagination. This provides rich behavioral context beyond the readOnlyHint and destructiveHint annotations.

  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 sentences, front-loaded with the core purpose, then adding safety and pagination details. Every sentence carries useful information without redundancy or rambling.

  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?

  Combined with comprehensive parameter descriptions and annotations, the description covers safety, row limits, truncation, paging, and ordering guidance. There is no output schema, but the description mentions the truncated flag, and the level of detail is sufficient for an AI agent to use the tool correctly.

  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?

  The input schema provides 100% description coverage for all four parameters, so the baseline is 3. The description adds operational context about truncation, paging, and ORDER BY best practices, but it does not significantly alter parameter meanings beyond what the schema already states.

  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 'Run a read-only SQL query and return rows', using a specific verb and resource. It distinguishes itself from specialized siblings by being the generic query runner, and the title reinforces the read-only scope.

  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 by focusing on read-only SQL and allowed statement types, but it does not explicitly tell when to use this tool versus alternatives like explain_query or list_schemas. There are no exclusions or alternative recommendations, leaving the choice somewhat inferred.

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

• security_postureA
  4.3/5.0
  Behavior4/5

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

  Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds context by stating the tool asks PostgreSQL rather than assuming, enumerates the specific checks performed, and reveals that it returns a grade plus fix commands. It also advises acting on alarming results. This goes beyond the annotations without contradicting them.

  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 no fluff. It front-loads the purpose, lists specific checks in a compact list, then states the output format and usage recommendation. Every clause adds value, making it appropriately sized for a security audit tool.

  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?

  Despite lacking an output schema, the description explains the return value (a grade and fix commands) and covers all relevant behavioral aspects. It also provides a usage context (session start) and what to do with results. For a tool with one optional parameter, this is complete and self-sufficient.

  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?

  The input schema has 100% coverage with a single optional 'database' parameter described as 'which configured database to use; omit when only one is configured.' The description does not add parameter-specific details, but the schema already fully covers it, meeting the baseline for schema-heavy tools.

  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 assesses the deployment's actual capabilities against the database (write, RLS bypass, file access, auth, encryption) and returns a grade with fix commands. It distinguishes itself from sibling tools like database_health and query by being a session-start security audit rather than a data operation. The verb is specific and the resource (security posture) is well defined.

  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 recommends calling this tool once at the start of a session and instructs the agent to communicate alarming results to the user. It does not explicitly mention alternatives, but given sibling tools, the context is clear. The guidance is useful and actionable, though not exhaustive on when not to use it.

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

• database_healthA
  4.5/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds valuable context: it is scoped to the current database and that unreadable items are reported as 'unavailable' rather than omitted. This explains permission handling and output completeness, going beyond the structured annotations.

  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 one well-structured sentence that front-loads the core purpose ('One snapshot...') and efficiently lists the included metrics. Every clause adds information (scope, permission behavior). No wasted words or 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 the tool's moderate complexity, the presence of annotations, and the absence of an output schema, the description is complete. It explains what metrics are included, the scope, and how permission limitations are handled. This is sufficient for an agent to invoke the tool and interpret the results without further documentation.

  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?

  The input schema has 100% description coverage for the single optional parameter 'database'. The description does not add meaning beyond the schema, but because the schema is sufficient, the baseline of 3 is appropriate. The description's reference to 'current database' indirectly relates to the parameter but does not enhance it.

  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 produces a snapshot of database health metrics (cache hit ratio, connections, long-running statements, vacuum backlog, etc.). It uses a specific verb ('snapshot') and resource ('database health'), and the scope ('current database') is explicit. It distinguishes from siblings like top_queries or list_tables, which focus on narrower concerns.

  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 implies usage as a one-stop health overview ('things an operator would otherwise assemble by hand'), which gives clear context for when to use it. However, it does not explicitly name alternatives or state when not to use it (e.g., when a specific metric is needed). This is a minor gap from full guidance.

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

• explain_queryA
  4.6/5.0
  Behavior5/5

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

  Adds crucial context beyond annotations: with analyze=true, it actually runs the query and reports measured timings and buffer usage, while remaining read-only and rolled back. This clarifies the real-world impact of the tool and aligns with the readOnlyHint and destructiveHint annotations.

  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?

  Three sentences, each serving a distinct purpose: purpose, analyze behavior, and usage guidance. No redundant or extraneous content.

  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?

  The description covers the primary use case, the behavior of the analyze flag, and safety guarantees. While no output schema exists, it hints at what the report includes (execution plan, timings, buffer usage). Could be slightly richer in detailing return structure or limitations, but it is largely complete for agent selection and invocation.

  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 67% (sql lacks a description). The description compensates by explaining that sql is the query to analyze and adding detail to analyze (runs the query, reports timings and buffer usage, still rolled back). Database is already described in 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 explicitly states the tool explains PostgreSQL execution plans for slow queries, with a specific verb and resource. It also distinguishes itself from sibling tools by pointing users to top_queries for which statement to analyze.

  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?

  Provides clear when-to-use guidance: apply to a specific statement, and directs users to top_queries as the alternative for discovering which statement to examine. Does not explicitly mention other sibling tools or exclusions, but the context is sufficient.

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

• simulate_indexA
  4.7/5.0
  Behavior5/5

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

  The description goes far beyond the readOnly/idempotent/destructive annotations by explaining the hypopg mechanism: index registered in backend memory only, gone when the call returns. It also discloses the failure mode if hypopg is missing and clarifies that results are planner estimates, not measured times. This aligns with annotations with no contradiction.

  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 dense yet well-structured, front-loading purpose and safety, then covering inputs, outputs, interpretation, and prerequisites. Every sentence earns its place; there is no filler or repetition.

  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 no output schema, the description fully explains what is returned: plan and cost with and without, plus whether the planner used the index. It also covers prerequisite, absence of side effects, and interpretation nuance, making it complete for a complex 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?

  The schema already covers 100% of parameters with descriptions, so baseline is 3. The description adds value by stating 'the index definition is assembled here,' clarifying that users supply table and columns rather than a full DDL statement, which goes beyond the schema's individual parameter descriptions.

  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 opens with 'Answers whether an index would change the plan for a given query — WITHOUT creating it,' a specific verb and resource. It explicitly distinguishes itself from sibling tools like analyze_indexes and explain_query by emphasizing 'the planner sees it, storage never does,' making the hypothetical nature unmistakable.

  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 gives clear usage guidance: provide query, table, and columns; the index is assembled automatically; no DDL can be sent. It also warns that these are estimates, not proof. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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