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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the payload (document, status, version, model reference) and by warning that the round-trip with save_onboarding_doc must preserve step keys and node ids. It does not state permissions scope or whether the returned document is a snapshot vs. live, which is why it is not a 5.

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 payload description is front-loaded and the editing guidance follows immediately; every clause carries information. The opening construction ('The JSON document ... is made of') is slightly convoluted, and the edit guidance could be one clause tighter, but there is 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?

With no output schema, the description carries the return-value burden and does so adequately for a single-parameter read: it names the document, its status, its version, and the model reference. The edit-in-place constraint on the round trip with save_onboarding_doc is the key behavioral fact an agent needs. Missing only error/empty cases (e.g. what happens for an unpublished or missing flow).

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 100% and the single `id` parameter is fully documented, including its provenance ('from list_surfaces'). The description adds no further meaning about the id. Baseline 3 applies when the schema does the heavy lifting.

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 concretely identifies the resource — the JSON document behind a builder-made onboarding flow — and enumerates what comes with it (status, version, document-model reference). Naming 'onboarding flow' also implicitly separates it from the paywall analog, though it never names get_paywall_doc/editor_get_doc explicitly. It is a noun phrase rather than a verb+resource, which costs a little crispness.

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 prerequisite ('Read this before save_onboarding_doc') and an operating rule ('edit the document you got rather than writing one from scratch — keep step keys and node ids, change only what was asked'). That is real when-to-use guidance. It stops short of naming exclusions, e.g. when editor_get_doc or validate_onboarding_doc should be preferred instead.

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