apply_schema_patch

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

With no annotations, the description carries the burden of behavioral disclosure. It clearly states that execution stops at the first failure, that atomic rollback is the default, and that dry_run=true returns the plan. This covers critical failure and preview behavior, though it omits details like permission requirements or whether changes persist to disk.

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 two sentences with no filler. The purpose is front-loaded, the operations list is compact, and behavioral notes are appended efficiently. It is well-structured and easy to parse.

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 complexity of a batch patch tool with many operation types and no output schema, the description covers the essential aspects: the operation list, atomicity, failure handling, and dry-run preview. It does not detail the response format or prerequisites like model availability, but the core information for correct invocation is present.

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. It explains the 'operations' parameter format and lists valid op values, and explains the effect of dry_run. However, it does not clarify the meaning or format of model_id, and atomic is only mentioned in passing, not fully defined as a parameter.

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 'apply' and the resource 'model', and enumerates a specific list of supported patch operations, which distinguishes it from individual sibling tools like create_table or drop_column. It conveys the batch nature of the operation effectively.

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 a batch use case through the ordered list and atomic rollback, but it does not explicitly state when to prefer this tool over calling individual sibling tools, nor does it mention prerequisites such as the model being open. The guidance is implicit rather than explicit.

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