willys_plan_add_recipe

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

With no annotations, the description carries full burden for behavioral disclosure. It discloses a key side effect: amounts are aggregated across recipes, so multiple recipes wanting eggs become one need. It also clearly states what the tool does NOT do (does not modify the cart). However, it does not mention auth requirements, return format, or error conditions, which keeps it from being fully transparent.

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?

Two sentences, front-loaded with the primary action, then aggregation behavior, then a clear alternative. No fluff or repetition; every sentence carries useful content.

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 tool with no output schema and no annotations, the description covers the core semantics well: what it adds, aggregation behavior, and separation from cart mutation. It lacks explicit return value info and a bit more context about plans, but overall it is sufficiently complete for an agent to invoke it 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?

Schema description coverage is about 50%, and the description adds context for how ingredients behave (e.g., aggregation key is the query term). The rich descriptions for ingredient subfields are in the schema, but the top-level 'ingredients' property and 'sessionId' remain inadequately described. The description offers some value but does not fully compensate for the gap.

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 opens with a specific verb and resource: 'Lägg ett recepts ingredienser i behovsregistret' (add a recipe's ingredients to the requirements register). It clearly distinguishes itself from cart-related siblings by stating 'Rör inte kundvagnen — kör willys_plan_apply för det' and from other plan tools by focusing on adding recipes.

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 explicitly tells the agent not to touch the cart and names the alternative tool (willys_plan_apply). It also provides actionable guidance on when to reuse a recipe name to replace instead of duplicate, and instructs scaling amounts to actual portions.

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