execute_sql

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

The description fails to disclose critical behavioral traits. With no annotations, the description should clarify that executing arbitrary SQL can modify or delete data, pose security risks, or require elevated permissions. The vague 'Execute any SQL query' leaves the agent unaware of potential destructive side effects.

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 extremely concise (4 words), which is appropriate for a simple tool. However, it sacrifices necessary detail, making it less useful. The structure is acceptable but would benefit from a brief mention of scope or limitations.

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?

Given the tool's high potential for side effects (executing any SQL), the description is dangerously incomplete. It lacks information about return values, error handling, isolation level, or whether modifications are committed. Without an output schema or annotations, the description must compensate, but it fails to do so.

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 input schema covers 100% of parameters, but the description adds no meaning beyond 'SQL to run.' The default value 'all' is unexplained and potentially misleading. The description should specify that the parameter expects a complete SQL statement, possibly including constraints like semicolons or transaction boundaries.

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 'Execute any SQL query' clearly states the action and resource, but is overly generic. It does not distinguish from sibling tools like explain_query or analyze_db_health, which also interact with SQL queries. A more specific purpose (e.g., 'Execute arbitrary SQL statements on the connected database') would improve clarity.

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 guidance is provided on when to use this tool versus alternatives. For example, it does not caution against using it for read-only analysis when explain_query might be safer. There is no mention of prerequisites or conditions (e.g., 'Use only if you need to modify data; otherwise prefer read-only tools').

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