run_readonly_sql

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 discloses that the tool is read-only, rejects mutation/DDL/multi-statement queries, and caps results at 100 rows. These are critical behavioral traits that an agent needs to know before invoking the tool, and they are all explicitly stated.

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 sentences, each carrying necessary information. The primary purpose is stated first, followed by usage guidance and security/result constraints. There is no redundancy or fluff; every sentence earns its place in the description.

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 role as a fallback SQL execution tool, the description covers all essential aspects: orientation to the dataset, usage restrictions, security boundaries, and result cap. An output schema exists (though not shown here), so the description needn't detail return formats. The description is complete for an agent to correctly decide when to use and how to invoke this tool.

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 schema has one parameter 'query' with zero description coverage. The description adds meaning by clarifying it is a SQL query, which matches the tool's purpose. Since there is only one parameter and it's inherently obvious from the tool name and description, the added context is sufficient, though it doesn't provide syntax examples or formatting details that could further enhance value.

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 states a specific verb ('executes'), a clear resource ('customers dataset'), and the read-only analytical nature of the query. It also explicitly positions it relative to sibling tools by stating it is only for when predefined analytics tools cannot answer, which clearly differentiates it from the listed siblings like get_churn_summary and describe_column.

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 states 'Use this tool only when the predefined analytics tools cannot answer the requested question', giving a precise when-to-use condition. It also implies when not to use (when predefined tools suffice) and lists security restrictions (mutation, DDL, multi-statement queries are rejected), providing clear operational boundaries.

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