FridgeToForks

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

With no annotations, the description carries the full burden and does so well: it discloses the dataset size, the non-obvious staple assumption (salt, oil, flour, spices and 380 others are never reported missing), what output includes (what is MISSING), and the exact ranking formula. It still omits operational details like rate limits, latency, or authentication requirements.

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 purpose is front-loaded, and every sentence adds useful information: dataset scope, staple assumption, missing-item reporting, ranking logic, and a usage trigger. There is no redundancy or filler.

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 two-parameter read tool with no annotations and no output schema, the description is quite complete on behavior, assumptions, and ranking. It is slightly thin on the exact return structure and on how to proceed from results to full recipe details, which the sibling tool could cover.

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 100% and the schema already explains that ingredients are free text with quantities ignored, and that max_results is 1-12 with default 6. The description adds result-semantics context (staples not counted as missing) but little parameter-specific meaning beyond what the schema already provides, so the baseline 3 applies.

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 states a specific verb and resource with scope: 'Search 100,000+ real recipes for ones that can be cooked from a given list of ingredients.' This is unambiguous against the sibling get_recipe_details, but it never explicitly names or contrasts with that sibling, so the differentiation is implicit rather than stated.

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 gives a clear trigger: 'Use this whenever someone asks what they can make from ingredients they already have.' However, it offers no exclusions, alternatives, or prerequisites (e.g., redirecting to get_recipe_details for full instructions), so it stops short of full when/when-not guidance.

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

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

With no annotations, the description carries the full burden and does well: it discloses that the FULL ingredient list and written method are withheld and gated behind a paid account, which is non-obvious behavior an agent must convey to a user. It does not cover error behavior or what happens with an invalid/stale recipe_id.

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?

Three tight sentences, front-loaded with what is returned, followed by input routing and then the paywall limitation. No filler.

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 2-parameter read tool with no output schema and no annotations, the description covers the essential return scope, the required upstream tool, and the deliberate omissions. It leaves the exact response shape and failure modes unspecified, a minor gap.

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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: recipe_id is tied to a prior find_recipes_from_ingredients result, and ingredients is framed as 'pass the cook's ingredients again' to compute this recipe's missing list — clarifying the two-step interaction the schema alone implies.

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?

Names a specific verb and resource ('Return the main ingredients, timings, servings and original source for one recipe') and explicitly distinguishes itself from the sibling by stating the recipe comes from find_recipes_from_ingredients. An agent can tell exactly what this returns versus what the discovery tool does.

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?

Explicitly routes the agent: the recipe must come from find_recipes_from_ingredients, and passing the cook's ingredients again yields the per-recipe missing list. It stops short of any when-not guidance or error-handling conditions, but the workflow context is clear.

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