执行只读 SELECT 查询

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses non-obvious runtime behavior: rejection of DML/DDL/multi-statements, three-layer result truncation with follow-up suggestions, and automatic re-read of big BIGINT keys as strings. No contradiction with annotations; context is added.

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 dense, purposeful sentences: core function, safety boundary, pagination pattern, and edge-case behavior. Nothing is wasted and the most important scoping 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?

The description covers return shape, safety, pagination, truncation, and big-integer handling, which is substantial for a query tool with no output schema. It stops short of describing error surfaces (e.g., exact rejection message or JSON framing), but the essential invocation knowledge is present.

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 schema already documents parameters. The description adds practical guidance: pagination values must go in params, DM8 native binding is verified, and params must never be used to interpolate identifiers. This is meaningful extra semantic context 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 opens by stating '执行一条 SELECT 语句，返回列名与结果行', giving a concrete verb, resource, and output. It further narrows scope by enumerating rejected statement types, which clearly distinguishes dm_query from read-only sibling tools like dm_explain or dm_table_sample.

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 explicitly says only SELECT statements are permitted and states how to paginate with LIMIT ? OFFSET ? and bound params. It does not explicitly name alternative sibling tools or say when to prefer them, but the inclusion/exclusion rules are unambiguous enough for an agent to decide when to call it.

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