snowflake_query

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

With no annotations provided, the description must carry the full behavioral burden. It discloses that the tool is read-only and returns structured rows with metadata, but it omits other important behavioral details such as timeout behavior, result truncation (beyond the schema default), permission requirements, or what happens with unusually large queries. The lack of annotations leaves significant behavioral gaps.

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 a single, front-loaded sentence with no redundancy. It states the action, the scope, and the result efficiently, making it easy to parse at a glance.

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 query tool in a large family of Snowflake operations, the description lacks crucial context: it does not mention that it supports only single statements, does not clarify if it uses the current warehouse, and does not reference any limitations or the presence of an output schema that could inform the agent. Given the abundance of sibling tools and the absence of annotations, this is insufficient for an agent to call it effectively in many scenarios.

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% and the description provides no additional meaning for the 'query' or 'max_rows' parameters. It does not explain the expected format of the query string, constraints on max_rows (e.g., limits), or the meaning of the default. The description adds zero value beyond the bare parameter names.

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 verb 'Execute' with a specific resource 'SQL SELECT or read-only query' and the result 'structured rows with metadata'. It distinguishes the tool from DML-focused siblings like snowflake_execute_dml by emphasizing the read-only nature, making its purpose unambiguous.

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 implies this tool is for read-only queries versus mutation tools like snowflake_execute_dml, but it does not explicitly state when to use this tool over other read-related tools (e.g., snowflake_get_query_history) or provide exclusions. The guidance is inferred rather than explicit.

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