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

Beyond the annotations (readOnly=false, openWorld=true, idempotent=true), the description discloses the concrete side effects an agent needs: it consumes one draft, may incur up to $0.02 of provider spend within the existing budget, and does not publish or send. It does not explain whether the call returns an asynchronous job handle, which is the main remaining behavioral gap.

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?

Four short sentences, front-loaded with purpose, then cost/side effects, then preconditions, then the negative boundary. No filler or repetition; each sentence carries distinct information.

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 non-read-only tool with no output schema, the description covers purpose, cost, side effects, idempotency requirement, and scope boundary – enough to invoke it safely. The missing piece is what the call returns (e.g., a preparation job id to poll via read_preparation_job), which an agent would still have to infer.

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% – only idempotencyKey is documented in the schema. The description compensates partially by clarifying that the actionId must refer to a "saved mapped action" and that an idempotency key is mandatory, but it says nothing about the optional workspace parameter, leaving a third of the inputs unexplained.

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?

"Queue a source-grounded draft for one saved mapped action" names a specific verb and resource, distinguishing it from read-only siblings like read_prepared_page_changes and read_preparation_action. It does not explicitly name a sibling it replaces or supersedes, which keeps it below a 5.

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 gives a clear precondition (requires an idempotency key) and an explicit boundary ("Does not publish or send"), which tells the agent this is a preparation step, not a deployment. It stops short of naming alternatives such as cancel_preparation_job or read_prepared_page_changes for inspecting results.

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