Update Recipe Draft

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

Beyond the annotations, it discloses concrete concurrency behavior ('Stale changes fail'), idempotent retry semantics ('Identical retries return the current draft'), and non-side-effects ('Does not publish or launch'). It also tells agents to preserve unedited fields and source bytes, which is operationally significant for a destructive update.

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 terse sentences, each carrying distinct operational information: source version, preservation rule, concurrency rule, idempotency, and side-effect exclusion. The most important action and precondition are front-loaded.

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 complex update with a large nested snapshot, the description covers the key operational concerns: obtaining the version, preserving unknown/unedited data, handling stale conflicts and retries, and avoiding confusion with publish/launch. The output schema exists, so return-value details are not required here.

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?

The description adds essential meaning to expected_version ('version from get_recipe_draft', stale changes fail) and to snapshot ('retain every unedited field, including original priors and source bytes'). draft_id and name are not explicitly explained, but their names are self-evident and the nested snapshot schema provides rich detail where the description is terse.

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 the action concretely: 'Replace authoring state' for a recipe draft, and specifies the source of truth ('version from get_recipe_draft'). It also carves out sibling behaviors with 'Does not publish or launch', distinguishing it from publish_recipe_draft and launch-related tools.

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?

Directs the correct workflow: call get_recipe_draft first, use its version, and if stale, reload and reconcile. It explicitly warns against expecting publish/launch side effects and gives a precise retry rule, leaving no ambiguity about when to invoke it.

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