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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description adds genuinely new behavior: this queues a hosted (asynchronous) job and its result must be fetched via get_job, and that the recipe is data-free/draft. That async workflow disclosure is valuable context beyond the annotations.

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?

Two sentences, front-loaded with the core action and followed by the retrieval instruction. Every clause earns its place with no filler.

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?

For a tool with six required parameters, deep nested objects, and no output schema, the description is thin. It omits the revision/idempotency contract, the structure of the transformation definition, and the full propose-then-review-then-apply lifecycle, so an agent cannot confidently construct a call from this text alone.

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 coverage is only 33% and the description says nothing about any of the six required parameters, including the complex nested 'definition' object, expectedRevision, projectId, or idempotencyKey. With low coverage the description should compensate but provides zero parameter meaning, so it falls below the baseline.

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 uses a specific verb+resource ("Create a draft... transformation recipe") and scopes it with "data-free" and "for later review," which distinguishes it from the sibling apply_transformation. It does not, however, name any sibling explicitly, so the differentiation is implied rather than stated.

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?

It signals the workflow (draft first, review later) and tells the agent to call get_job to retrieve the result, which is useful routing. But it never states when to pick this over apply_transformation, nor what triggers the subsequent apply step, leaving the core when-to-use decision to inference.

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