snowflake_clone_table_recipe

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the tool uses time travel (timestamp/statement ID), but omits critical traits: whether it overwrites an existing target, whether it is destructive, what happens if the target exists, required privileges (e.g., AT/BEFORE clause support), and what the composite recipe actually does step-by-step. This is insufficient for a mutation-like operation.

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 one sentence, efficient and front-loaded with the core functionality. However, it is almost too terse: the term 'Composite recipe' is jargon, and the sentence does not structure information in a way that clearly separates the purpose from usage notes. Still, no fluff and good brevity.

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 is labeled a 'composite recipe' (likely a multi-step operation), the description lacks crucial context: what the recipe entails (e.g., cloning plus a lookup or DDL generation), any prerequisites, and limitations. The output schema exists, so return values are covered, but the absence of behavioral and usage context makes this incomplete for an agent to invoke correctly.

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 explain parameter semantics. It only hints that at_or_before accepts a timestamp or statement ID, but does not detail formats, defaults, or the relationship between source_table and target_table. Names are self-explanatory but no additional meaning is added, leaving agents to guess about the parameter usage.

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 the tool clones a table with Time Travel support (timestamp or statement ID), which is a specific verb+resource. It implicitly differentiates from snowflake_clone_table by mentioning time travel, but the term 'Composite recipe' is vague and could confuse agents about what the recipe entails. Still, the core purpose is clear.

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 gives no explicit guidance on when to use this tool versus the sibling snowflake_clone_table. It does not mention that this should be used when time travel is needed, nor does it describe any exclusions or alternatives. The phrase 'Composite recipe' implies a convenience wrapper but does not explain the selection criteria.

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