SQL 审核检测

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

Annotations already convey read-only and idempotent behavior. The description adds useful context: it's a pre-submission check, maps to a specific API endpoint, and rejects SELECT statements. 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.

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

Three concise sentences, each providing essential information: purpose, usage order, and a key exclusion. No redundant content; front-loaded with the primary function.

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 no output schema, the description explains purpose, usage, and constraints, which is mostly sufficient. It lacks detail on the return value/audit result, but the 'response_format' parameter hints there is a formatted output. Overall, it covers the key contextual needs.

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 descriptions cover 80% of parameters. The description adds a critical semantic constraint on the 'sql' parameter by explicitly stating SELECT is not accepted, clarifying it should be DDL/DML. This provides meaning beyond the schema's field descriptions.

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 performs SQL review before submission with a specific verb and resource ('对 SQL 做审核检测'). It distinguishes itself from siblings by mentioning the intended sequence with yearning_submit_order and explicitly excluding SELECT (delegating to yearning_run_query).

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 provides explicit when-to-use guidance ('建议先调用本工具，再 yearning_submit_order') and an alternative for SELECT queries ('请用 yearning_run_query'). This is concrete and distinguishes from sibling tools.

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