search_recipes

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

Annotations declare readOnlyHint, openWorldHint, and idempotentHint, reducing the burden on the description. The description confirms read-only behavior ('Search recipes'). However, it doesn't disclose pagination behavior (the page_number parameter exists but isn't mentioned), rate limits, or that the 'open world' hint means it may search external sources. This is adequate but not enhanced beyond annotations.

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 a single, concise sentence that lists key filter categories without unnecessary words. It front-loads the purpose ('Search recipes') and then enumerates filter types efficiently. Could potentially be slightly more detailed without becoming verbose.

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 17 parameters, no output schema, and low schema coverage, the description is moderately insufficient. It provides enough for simple searches but lacks specifics on filter range semantics, result ordering (sort_by), pagination, and the matchall boolean. The annotations (readOnlyHint, openWorldHint) compensate partially, but return format is completely unaddressed.

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 only 6% (only search_expression has a description), so the description must compensate. While it lists parameter categories (calories, macros, prep time, recipe types), it doesn't explain the 'from'/'to' range semantics, how sort_by works, what recipe_types_matchall means, or the relationship between search_expression and other filters. This is insufficient for 17 parameters.

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 'Search recipes with optional filters', specifying both the verb (Search) and resource (recipes). The mention of specific filter types (calories, macros, prep time, recipe types) distinguishes it from sibling tools like search_foods or get_recipe. However, it doesn't explicitly differentiate from get_recipe which might be a singular recipe lookup, leaving slight ambiguity.

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 no guidance on when to use this tool vs siblings like search_foods or get_recipe. It doesn't mention that this is for recipe-specific search versus food search, nor does it specify when not to use it. The openWorldHint annotation suggests it works with external data but this isn't explained.

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