Snowflake Cortex Extract Answer

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

Annotations declare readOnlyHint=true and openWorldHint=true, so the agent knows it's a read-only external-call operation. The description adds nothing beyond this – no model behavior, latency, token limits, or whether the answer is grounded or hallucination-prone. For a Cortex LLM tool, this is a significant gap.

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?

A single front-loaded sentence with no waste. It is concise, though very minimal for the complexity of an LLM extraction tool.

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 this is an LLM-based extraction tool with openWorldHint, the description is too sparse. It omits usage boundaries vs. sibling Cortex tools, input format expectations, and any behavioral caveats. Output schema exists, so return values needn't be described, but much else is missing.

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 doesn't clarify what 'source_text' and 'question' mean beyond the names. For example, it doesn't say whether source_text must be a single document or can be concatenated, or question phrasing constraints. With an output schema present, return semantics are handled, but parameter semantics are weak.

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?

States a specific verb+resource: extract a direct answer to a question from unstructured source text. An agent can distinguish it from siblings like cortex_complete and cortex_summarize. However, it does not explicitly contrast itself with the sibling cortex_summarize or other Cortex text tools.

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 on when to use this over cortex_summarize, cortex_complete, or cortex_search. It implies a question-answering use case but doesn't state exclusions, prerequisites, or alternative selection criteria.

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