willys_plan_set_ingredient

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It communicates that the tool modifies only one ingredient without affecting others ('utan att röra de andra') and can both add and correct. However, it does not mention error behavior, permissions, or what happens if the recipe does not exist, leaving some gaps for a mutation-only tool.

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 description is two sentences, front-loads the primary purpose, and then gives a concrete usage scenario. No filler or redundant information, making it highly efficient.

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?

Despite having no output schema or annotations, the combination of the focused description and the detailed input schema covers the main use case well. It explains what the tool does, when to use it, and the schema documents parameter semantics thoroughly. Missing details like return values and edge cases are not critical for this targeted update operation.

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 itself adds no parameter-level detail, but the input schema already provides rich descriptions for most parameters, including the nested ingredient object fields (query, amount, mustContain, etc.). With top-level schema coverage at 50% and nested properties well described, the description's lack of param info is acceptable but not compensated beyond the baseline.

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 clearly states 'Lägg till eller rätta EN ingrediens i ett recept' (add or correct one ingredient), giving a specific verb and resource. It also distinguishes itself from willys_plan_add_recipe by explicitly positioning it as a fix for a single mismatched row rather than resending the whole recipe.

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?

The description provides explicit guidance: 'Använd detta för att fixa en felmatchad rad (t.ex. skärpa mustContain) i stället för att skicka om hela receptet med willys_plan_add_recipe.' This clearly states when to use the tool and names the alternative tool, making the usage context unambiguous.

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