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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description reinforces rather than repeats them with operational detail: the saved change is exactly the previewed one, retrying with the same proposal_id never saves twice, and proposals expire after ten minutes. These are exactly the non-obvious behavioral facts an agent needs for a destructive, idempotent write.

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 consent precondition is front-loaded in the first two sentences, followed by guarantees, the retry rule, the alternative path, and the expiry limit, with no filler. Every sentence carries a distinct actionable constraint.

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?

With only two required parameters and an output schema that covers return values, the description supplies everything else an agent needs: consent gating, equivalence of result to preview, idempotent retry on unknown outcome, expiry window, and the escape hatch of a new prepare call. Nothing material is missing for a destructive two-parameter tool.

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 100%, so both parameters are already documented and the baseline would be 3. The description still earns credit by explaining the retry contract of proposal_id ('call again with the same proposal_id') and the timing/consent contract of approval, which the schema field text states only in abbreviated form.

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 opening sentence states a specific verb and resource ('Save a prepared change') and constrains it with a condition ('after the user approved it'), which immediately distinguishes it from the d8a_prepare_* siblings that only build previews. An agent can tell which side of the prepare/execute pair this is without inspecting the schema.

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?

Explicit preconditions are given ('First show the user the complete preview from the prepare tool and ask them to confirm; call this only after they agree'), along with a named alternative for the divergent case ('If the user wants something different, prepare a new preview instead'). The retry path for unknown outcomes is also routed explicitly, so no when/when-not decision is left to inference.

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