run_query

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

No annotations are provided, so the description carries the full burden. It explicitly states the tool is read-only and only permits SELECT/WITH statements. It does not mention authentication, rate limits, or error handling, but the key behavioral trait (safety) is well communicated.

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 three sentences plus an example, all front-loaded with the core purpose. Every sentence adds useful information without redundancy. It is concise and well-structured.

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 that an output schema exists, the description does not need to explain return values. It covers purpose, constraints, and provides an example. It could mention performance or error handling, but for a simple SQL tool, it is largely 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 description coverage is 0%, so the description must compensate, but it does not explain the 'sql' or 'limit' parameters individually. The example shows usage but does not clarify that 'limit' defaults to 200. The description adds minimal semantic 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 immediately states 'Run a READ-ONLY SQL query against the job DB for ad-hoc pattern analysis', clearly specifying the action, resource, and purpose. It distinguishes itself from sibling tools which are mostly mutation tools (e.g., add_jobs, update_job).

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 explicitly restricts usage to SELECT/WITH statements and mentions enforcement on a read-only connection. It provides a list of handy tables and an example, guiding the user on when to use it (ad-hoc analysis). It does not explicitly state when not to use, but the read-only constraint is clear.

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