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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description adds that it makes no AI call, saves nothing, and requires a linked Chop It account — the auth prerequisite is exactly the kind of context annotations cannot carry. It also explains the token is a signed, user-visible copy holding no secret and granting no access, which prevents an agent from misreading it as a capability grant.

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 key facts — what is returned, the save_recipe contract, side-effect freedom, and the account prerequisite — are front-loaded in four dense sentences. The token security aside is slightly over-explained, but it earns its place by heading off a plausible agent misconception.

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?

An output schema exists, so return values need no prose, and the description still covers the workflow dependency, safety profile, and auth requirement. The remaining gap is input guidance for the undocumented parameters, which matters for a tool whose output quality depends on pantryMode and focusIngredients being set correctly.

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?

With 57% schema coverage and 7 parameters, several inputs (servings, pantryMode enum values, focusIngredients) carry no explanation in either schema or description. The description gestures at pantry context, which maps loosely to pantryMode, but does not distinguish pantryMode='use' from 'focus' or explain how focusIngredients interacts with it.

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 uses a specific verb and names the concrete artifacts returned: the recipe brief (structure, UK ingredient names, metric quantities, method detail), pantry context, and a recipeDraftToken. It explicitly contrasts with the sibling save_recipe, which consumes the token, so an agent can place it in the workflow without opening 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?

Usage is clearly implied and partly explicit: call this to obtain the brief before writing a recipe, and pantry context is included 'when the user wants to cook from their pantry'. It does not, however, state exclusions against adjacent siblings like import_recipe_from_url, search_recipes, or save_discovered_recipe, so the alternative-selection guidance is incomplete.

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