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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: the call is asynchronous (queues a hosted job), the result must be fetched via get_job, and human approval must be real rather than fabricated. It stops short of describing state effects on the recipe (e.g., whether approval is reversible).

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?

Three short sentences, front-loaded with the action and purpose, then the async pattern, then the approval warning. Slight overlap between 'with recorded human approval' and 'do not fabricate approval fields', but nothing is wasted.

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?

Covers the async job pattern and the human-approval prerequisite, which are the highest-risk behaviors for a 9-parameter, all-required mutation tool with no output schema. However, with low schema coverage it omits revision-conflict handling, idempotency semantics, and the effect of the decision on the recipe's lifecycle.

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 only 22% across 9 required parameters, so the description is expected to compensate, yet it only alludes to the approval object ('do not fabricate approval fields'). Key semantics such as expectedRevision (optimistic concurrency), idempotencyKey, workspaceToken, decision, and note are left entirely to bare schema types.

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?

States a specific verb pair (approve/reject) and resource (draft transformation recipe) with the recorded-approval qualifier. An agent can distinguish it from propose_transformation, apply_transformation, and undo_transformation without opening schemas.

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?

Gives a clear precondition ('Obtain actual user approval before calling; do not fabricate approval fields') and names the follow-up path ('Queues a hosted job; use get_job to retrieve its result'). It does not explicitly contrast with apply_transformation or undo_transformation, but the approval-workflow context is unmistakable.

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