clone_catalog

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

With no annotations provided, the description carries full burden, and it delivers exceptionally well. It discloses the three-stage execution process (schema creation, async data copy, FK application), asset handling modes ('none', 'refs', 'full') and their implications, orphan handling strategies, and the fact that it uses export annotations to determine reachability. It also explains potential side effects like 'truncate_oversized' and 'prune_hidden_fkeys'. This goes far beyond typical descriptions.

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 long but appropriately structured with sections for asset handling, orphan handling, and an Args list. There is some redundancy (e.g., asset_mode and orphan_strategy are explained both in dedicated sections and again in the Args list), which adds slight verbosity. However, the information is well-organized and every sentence contributes meaning; the complexity of the tool justifies the length.

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 complexity (19 params, no annotations, and an output schema), the description is remarkably complete. It covers the return format ('JSON with status...'), provides a concrete example, details the multi-stage process, and clarifies all major parameters. The output schema is not shown, but the description summarizes what it returns, which is sufficient for an agent to understand the result shape.

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 for all 19 parameters. The Args section provides a meaningful description for every single parameter, including defaults and examples (e.g., source_hostname 'www.facebase.org', root_rid '3-HXMC'). It explains nuanced behavior like orphan_strategy and asset_mode, adding substantial value beyond the bare schema titles and defaults.

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 purpose: 'Create an ML workspace by cloning data reachable from a root RID.' It uses a specific verb ('Create') and resource ('ML workspace'), and distinguishes itself from siblings by emphasizing a 'partial catalog clone' and focusing on root-RID reachability. This is unique among the sibling tools, making the purpose unmistakable.

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 provides clear context on when to use the tool (e.g., cloning data from a project, dataset, or experiment) and explains the high-level workflow (three-stage approach, asset handling modes). It does not explicitly contrast with clone_catalog_async, but the detailed parameter guidance (e.g., orphan_strategy, asset_mode) effectively implies appropriate use cases. No explicit exclusions are given, but the examples and mode explanations serve as practical guidance.

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