run_query

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the read-only enforcement (SELECT/WITH/EXPLAIN), a hard 500-row cap, and a 30-second timeout — exactly the operational traits an agent needs. It omits what happens on rejection or how to page past 500 rows, so it is strong but not exhaustive.

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?

Four sentences, front-loaded with what the tool does before the constraints, then syntax and domain tips. Every sentence carries information, though the weighting advice sits slightly apart from the query-execution mechanics.

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?

An output schema exists so return values need not be described, and the description still covers safety, limits, timeout, and identifier-quoting pitfalls. With no annotations to lean on, the remaining gap is error behavior and pagination semantics beyond the 500-row ceiling.

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%, so the baseline is 3, but the description adds real semantics: the allowed statement classes for the sql parameter, the requirement to double-quote uppercase identifiers, and the weight-column convention for aggregate metrics. The limit parameter's 500-row ceiling is stated, though the description doesn't explain how it interacts with the server-side cap.

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?

States a specific verb+resource ('执行一条只读 SQL 查询并返回结果') with the scope qualifier '只读'. It is clearly distinguishable in practice from metadata-oriented siblings like describe_table and sample_rows, but it never names an alternative, so it stops short of explicit sibling differentiation.

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 defines the usage envelope (read-only statements only, 500-row cap, 30s timeout, weighting advice for aggregate metrics), which implicitly tells the agent when this tool applies. However, it never says when to prefer run_query over describe_table, sample_rows, variable_stats, or plot_variable, so routing guidance is left to inference.

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