create_transformation

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

No annotations are provided, so the description must carry the full burden. It discloses the write-only behavior and refusal in read-only sessions, which is a key behavioral trait. However, it does not disclose other behaviors such as behavior on duplicate names, potential error conditions, or any side effects beyond creation. Given the absence of annotations, this is a partial disclosure.

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 concise paragraph followed by a clearly formatted Args list. The purpose is front-loaded in the first sentence, the write-access caveat is placed next, and each parameter is given a single line. There is no redundancy; every sentence earns its place.

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?

The tool has 5 parameters, an output schema, and no annotations. The description covers the write-access constraint, all parameter semantics, and the default schema. It does not describe the return value, but since an output schema exists, that is acceptable per the rubric. It also doesn't mention error handling, but for a creation tool this is a minor gap. Overall, it is sufficiently complete for an agent to call it 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?

The input schema provides only titles and defaults; there are no per-parameter descriptions. The description compensates fully: it explains the name validation pattern, the SQL body content (dbt-compatible with ref(), source(), Jinja), the allowed materialization values, and the default schema. This is far more than the schema offers, so it adds significant value.

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 opens with a specific verb+resource: 'Create a new dbt SQL transformation.' It clearly distinguishes from sibling creation tools (create_connection, create_upload, create_pipeline) by naming the resource type. The write-access caveat is contextual but not confusing.

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 explicitly states the write-access requirement and that read-only sessions refuse the call, which is a clear usage context. However, it does not mention alternative tools for other operations (e.g., compile_transformation) or explicitly state when not to use it beyond the write-access condition. Thus, it has clear context but no exclusions.

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