run_sql

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

No annotations provided, so the description must bear full burden. It does not disclose whether SQL queries can be write operations (e.g., INSERT/UPDATE/DELETE) or only reads. The example shows a SELECT, but this is insufficient to infer safety.

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 relatively short but includes a lengthy example. It is front-loaded with the purpose but contains some waste (e.g., repeating server info). Could be more concise while adding missing details.

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 has 4 parameters, no annotations, and an output schema, the description leaves significant gaps: no detail on return format, no pagination handling, and no behavioral constraints. It is only partially complete.

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 0%, so description must explain all parameters. It covers 'query' and 'server' but omits 'page' and 'size', which are left to defaults with no explanation of their purpose (likely pagination).

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 runs a SQL query against log/alert data and provides an example. It identifies the resource (UTMStack SQL editor) and action, but does not explicitly differentiate from sibling tools like search_logs.

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?

The description includes an example and notes on index naming and server targeting. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., search_logs) or when not to use it.

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