execute_sql

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

With no annotations, the description carries the full burden of disclosing behavior, but it only says SQL statements are executed. It does not state whether the tool is read-only, whether commits occur, what SQL dialects or operations are allowed, what happens with destructive statements, or what the response contains. The '强制限定配置' phrase suggests restriction but fails to define it concretely.

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 appropriately short and front-loads the main purpose before listing parameters. The parameter list is easy to scan and avoids excessive detail. The parenthetical is somewhat cryptic, but no sentences are wasted.

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 named execute_sql with multiple siblings, no annotations, and a potentially dangerous operation, the description is incomplete. It omits allowed SQL statement types, result format, pagination behavior, error handling, and security restrictions. An agent cannot confidently decide whether this tool will safely execute a given SQL statement or whether to choose execute_sql_file or list_tables instead.

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 0%, so the description must compensate. The parameter list restates the schema names but does add minimal meaning: limit is for pagination, offset skips rows, and fetch_results controls result return. However, it does not explain how these interact, whether limit/offset apply to all statements or only queries, or what constraints exist on the sql parameter.

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 identifies the core action: '执行 SQL 语句' (execute SQL statements). The parenthetical '强制限定配置下的SCHEMA操作' adds some scoping, suggesting operations are constrained, but it is vague about whether this means schema-only, read-only, or sandboxed execution. It is distinguishable from execute_sql_file because it executes a raw SQL string rather than a file.

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?

No explicit guidance is given about when to use this tool versus its siblings like execute_sql_file, list_tables, or switch_schema. The parenthetical hints at a restricted configuration but never states the conditions under which execute_sql is appropriate or when another tool should be chosen. An agent is left to infer usage context.

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