执行查询

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

Annotations already declare readOnlyHint and destructiveHint, and the description adds that query permission is required and that audit may require a prior submission order, which is valuable behavioral context. It also notes the msgpack transport, disclosing the response format underlying the tool. No contradiction with annotations.

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 compact sentence that front-loads the core action, then tacks on constraints and the endpoint reference. Every clause 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 read-only query tool with good annotations and schema, the description includes permissions, audit workflow, and the underlying protocol. It could mention how to handle long-running queries or the relationship to `yearning_sql_check`, but it's otherwise complete for the tool's purpose.

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 covers 4 of 5 parameters with descriptions (80% coverage), so the baseline is 3. The description adds no additional parameter-level semantics beyond reinforcing that SQL must be SELECT, which is already in the schema. Therefore, no extra 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 uses a specific verb ('执行') and resource ('指定数据源') with a clear read-only SELECT scope, and distinguishes from siblings like `yearning_sql_check` and `yearning_submit_query_order` by indicating this executes the query directly. It also references the underlying WS endpoint, further clarifying its role.

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 states a prerequisite (query permission) and a conditional alternative: if audit is on, first use `yearning_submit_query_order`. This gives clear when-to-use guidance, though it doesn't compare with other sibling query-related tools like `yearning_sql_check`, so 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.