Suggest recipes

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

The annotations already declare readOnlyHint=true, so the agent knows this is a safe query. The description adds important behavioral context: the tool returns nothing on plain-text ingredient collections, and the ranking is by 'how little is missing.' This exceeds what annotations provide. A score of 5 would require additional details like pagination or return format.

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 three sentences long with no wasted words. Each sentence serves a distinct purpose: stating what the tool does, defining prerequisites, and providing an alternative. It is front-loaded with the core action.

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?

Given the 5 parameters (all optional), 80% schema coverage, no output schema, and the complexity of ranking logic, the description adequately covers what an agent needs to know to decide when and how to invoke this tool. The prerequisites and alternative are clearly stated.

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 80%, and the description mostly explains the overall function rather than each parameter. It mentions that foods and tools come from the pantry, which aligns with the schema, but doesn't elaborate on 'max_missing_foods' or 'max_missing_tools' beyond what the schema already says. The description adds minimal parameter-level value.

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 specific verbs ('suggests', 'ranked by how little is missing') and clearly identifies the resource ('recipes that can be cooked from foods and tools marked as "on hand" in Mealie'). It distinguishes itself from the sibling 'search_recipes' by explaining the ranking logic and the prerequisite of structured data.

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 explicitly states when this tool is appropriate (instance with structured foods, units, and on-hand pantry) and when it is not ('on a collection of plain text ingredients it returns nothing'). It provides a clear alternative: 'Use search_recipes there.'

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