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

No annotations are provided, so the description carries the full burden. It discloses that the tool does not perform the action itself but returns commands for the user to run, and it warns against fabricating commands. It could add more detail about the output format (e.g., whether it returns a list of commands or a single string), but the core behavioral trait is clearly disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: it states the trigger condition, the security rationale, and the required agent behavior in three sentences. Every sentence earns its place, and there is no redundant information.

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

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

For a tool with one optional parameter and no output schema, the description is quite complete. It explains the purpose, the security constraint, and the expected agent behavior. It could be slightly more explicit about what the return value looks like (e.g., a list of commands), but given the simplicity of the tool, this is a minor gap.

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

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

Schema coverage is 100% and the single parameter has a clear enum with descriptions. The description adds context by explaining the overall purpose of the task parameter (which operation the user wants), but the schema already covers the parameter well. The description's mention of the five task types aligns with the enum, so it adds modest value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific purpose: it returns terminal commands for DB connection management tasks (add/delete/edit credentials/rename alias) that the AI cannot perform directly. It clearly distinguishes itself from siblings like list_connections or run_select_query by focusing on generating user-facing commands rather than executing operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use it (when the user wants to add/delete/modify DB connections or aliases) and why (security: AI cannot perform these directly). It also instructs the agent to present the returned commands verbatim and not to invent commands, which is clear usage guidance.

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

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

No annotations are provided, so the description carries the behavioral disclosure burden. It discloses what is returned (up to 10 select/write queries in latest order) and what is deliberately not stored or returned (query results and connection info), providing useful expectations beyond the empty schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each earning its place: core behavior, trigger condition, and limitation. It is front-loaded and contains no redundant phrasing.

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

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

For a zero-parameter, no-output-schema history-retrieval tool, the description covers the return cap, ordering, trigger context, and exclusions. An agent can confidently call it and interpret the outcome without additional metadata.

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

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

The tool has zero parameters and schema coverage is 100%, so no parameter documentation is required; the baseline for zero-parameter tools is 4. The description adds return-semantics context rather than input details, which is appropriate here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('반환한다') and resource ('최근 실행한 쿼리(select/write)') with clear constraints: maximum 10, latest first. This unambiguously distinguishes it from siblings like run_select_query, run_write_query, 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.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger condition: call when the user asks '방금/최근에 무슨 쿼리 실행했어?'. It does not explicitly state when not to use it or name alternatives, but the context is clear enough for an agent to select this tool.

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

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

No annotations are provided, so the description carries the transparency burden. It conveys read-only intent ('조회') and the output content, but does not address prerequisites, error behavior, or whether the list is complete or ordered. For a simple non-mutating list this is adequate but not detailed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: the first states the result, the second gives the user-interaction usage rule. No filler, and the key information is front-loaded.

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

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

For a parameterless listing tool, the description covers what it returns and when to use it. It could add a note on output shape/ordering or side-effect safety, but no output schema exists, so the description is nearly complete.

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

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

The tool has zero parameters and the schema documents this with 100% coverage, so there is no parameter meaning for the description to add. Baseline 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states a specific action ('retrieves list of registered DB connections') and the returned content ('numbers and aliases'). This clearly differentiates it from sibling query/write/test tools that operate on an already-chosen connection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger: when the target DB is ambiguous, show the list to the user and ask them to pick a number. However, it does not name sibling tools or state when not to use it, so it is not a complete routing guide.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states the tool is read-only and rejects data-modifying queries, which is the most important behavioral trait. It does not detail error handling or result formatting, but for a simple execution tool this 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single succinct sentence that front-loads the core purpose and the critical restriction (rejecting write queries). Every word earns its place; no fluff or redundancy.

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

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

For a tool with only 2 parameters and full schema coverage, the description provides sufficient context: it tells the agent what the tool does, that it's read-only, and that connection_no comes from list_connections. The absence of an output schema means no return format is expected, so the description is complete enough for correct invocation.

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

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

The schema already fully documents both parameters with clear descriptions (query as read-only SQL, connection_no from list_connections). The description adds no new semantic detail beyond reinforcing the read-only nature, so the baseline of 3 applies as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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 queries (SELECT, SHOW, DESC, EXPLAIN) and returns results. It explicitly distinguishes itself from the sibling run_write_query by stating that data-modifying queries are rejected, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use this tool (for read-only operations) and sets the boundary against write queries. It also references list_connections for obtaining connection_no, implying a prerequisite step. However, it doesn't explicitly name the alternative tool for write operations, though it's implied by the tool naming and the rejection statement.

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

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

The description discloses critical behavioral traits: it requires user approval before execution, Claude Code permission settings (ask) will double-check right before execution, and read-only connections will be forcibly rejected by the server. These are important behavioral details beyond what annotations would provide. Since no annotations are provided, the description carries the full burden and does it well, though it could mention what happens on failure or the return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the core purpose, then adds essential behavioral warnings. It's three sentences with no wasted words. It could be slightly more structured, but it's efficient and informative.

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

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

For a mutation tool with no annotations and no output schema, the description covers the key operational context: what it does, the approval requirement, the double-check mechanism, and the read-only rejection behavior. It doesn't describe the return value or error handling, but for a write tool that's less critical. The sibling context (run_select_query exists) makes the read/write distinction clear.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (query and connection_no). The description adds context that the query is a single SQL statement (DML/DDL) and that connection_no comes from list_connections, which is helpful. However, it doesn't add much beyond the schema's own descriptions, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool executes data-modifying SQL queries (INSERT/UPDATE/DELETE/DDL), distinguishing it from read-only query tools. The verb '실행한다' (executes) with the specific resource (data-changing queries) makes the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool: for data-modifying queries, and it implicitly contrasts with read-only connections. It also mentions the approval requirement before execution. However, it doesn't explicitly name the sibling alternative (run_select_query) for read-only queries, so it's not a full 5.

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

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

With no annotations, the description carries the full transparency burden. It discloses that the tool performs a real SELECT 1 connection test, that it does not expose connection information or data, and that it only returns success/failure. This covers the key behavioral traits, though it omits potential timeout or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loaded with the core action and then the result behavior. 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.

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

For a single-parameter tool with no output schema, the description sufficiently explains what it does and what it returns. It does not mention prerequisites or failure details, but the schema's parameter description already references list_connections, so the overall definition is fairly complete.

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

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

Schema description coverage is 100% for the sole parameter connection_no, including an example from list_connections. The description's reference to '지정한 번호' adds little beyond the schema, 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.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to verify actual connectivity to the specified DB connection number via SELECT 1. It also distinguishes itself from data-returning queries by explicitly noting that it only returns success/failure and does not expose connection info or data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The use case is implied — use this tool to check connectivity — but the description does not explicitly contrast it with siblings like run_select_query or list_connections, nor does it state when not to use it. An agent can infer the purpose, but explicit routing guidance is absent.

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