Recipes Daily

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

The annotations (readOnlyHint: true, idempotentHint: true) already establish safety. The description adds materially by disclosing the matching heuristic (text-based matching, not identity — near-misses count, while synonym pairs like courgette/zucchini may fail) and the partial-match fallback behavior (returns closest partial matches rather than erroring). This is exactly the kind of behavioral nuance an agent needs to interpret results correctly. No contradiction with 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?

Three sentences cover purpose, matching heuristic, and responsibility boundary without redundancy. The first sentence is front-loaded with the core function. However, the second sentence's caveat chain ('a near-miss on the name still counts, but...') is slightly convoluted to parse, though each clause earns its place.

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 read-only, idempotent ranking tool, the description comprehensively covers what the agent needs: ranking logic, matching semantics, partial-match behavior, and caller responsibility. The only minor gap is no description of the return format, but since there's no output schema and the tool is non-destructive, the cost of this gap is low. The description fully compensates for the lack of enum constraints or nested complexity.

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% — both `ingredients` (with example) and `limit` (with default and bounds) are well-documented in the schema itself. The description's matching semantics do enrich how one understands the `ingredients` param, but this is incidental rather than a direct param explanation. Since the schema carries the load, the baseline of 3 is appropriate.

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 a specific verb ('rank'), resource ('recipes at recipes-daily.com'), and ranking criterion ('by how many of them each one uses'). It goes beyond a generic statement by scoping the ranking behavior and how the tool communicates missing ingredients, which distinguishes it meaningfully from the sibling tool search_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?

The description gives clear context on when to use this tool (when you have a list of ingredients and want recipes ranked by coverage) and explicitly states what it is NOT ('not a substitution finder') and that the caller is responsible for substitution decisions. It stops short of explicitly naming the sibling alternative, but the boundary is well-drawn.

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?

Annotations already declare the tool read-only and idempotent, and the description adds meaningful behavioral details beyond that: every query word must appear in one recipe, multiple ingredient terms can cause empty results rather than a coverage report, and the return is a shortlist with title, URL, description, time, servings, and categories. It also explains the rationale that results are real pages, not remembered guesses.

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 front-loaded with the primary use case and remains information-dense despite its length. Each sentence contributes useful practical context, such as when to use the tool, how it differs from the sibling, and what its result payload looks like. There is no filler or repetition pulling away from the essential 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?

With no output schema present, the description compensates by listing exactly what the shortlist returns, including title, URL, description, total time, servings, and categories. The schema complements pagination and parameter details, while the description gives the matching behavior and the rationale for using the tool rather than guessing. It feels complete enough for selection and invocation.

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?

Since the input schema covers 100% of the parameters, the baseline is a 3, but the description adds valuable insight beyond the schema. It explains that every query word must appear in a single recipe, that ingredient-packed searches will have no results, and that omitting the parameter lists every recipe newest-first—details that make invocation predictable.

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 concrete action, 'Find something to cook,' and clearly identifies the resource as recipes published at recipes-daily.com. It also distinguishes this tool from its sibling, find_recipes_by_ingredients, by explaining the input-matching difference, so an agent can immediately tell them apart.

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 says to call this tool for any question about what to make, including dish names, cuisines, time budgets, or a week of dinners. It then directs users to the sibling for ingredient-based requests and even explains the failure mode of using this tool that way. This provides both clear when-to-use and clear when-not-to-use 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?

Using the helpful readOnlyHint and idempotentHint annotations as a baseline, the description adds valuable context: cards 'appear only if you call this,' preserving the client-side visual behavior, and that order is kept. It discloses that the tool is the actual access mechanism for recipes. This goes beyond bare annotations without over-explaining.

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 leads with the core behavior, then explains the context, and ends with an actionable ordering rule. Each sentence earns its place and avoids redundancy. It is compact yet complete for a tool of this simplicity.

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?

The tool has one straightforward parameter, no output schema needed, and annotations document read safety and idempotency. The description fully covers what to do, when to do it, and how the result behaves. For this simple card-rendering tool, there are no important missing context gaps.

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 input schema already covers the parameter fully: type, constraints, format, and order semantics are all described. The description repeats the 'put the strongest recommendation first' ordering guidance but does not provide additional meaning beyond the schema's high coverage. Therefore, the baseline of 3 is appropriate.

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 identifies the tool's action ("Draw recipes as picture cards") and distinguishes it from sibling search/find tools by specifying that it displays already-held recipe URLs. The phrase "the cards are how a person actually gets to a recipe" reinforces the display purpose. This is a specific verb+resource pairing with clear sibling differentiation.

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 an explicit when-to-use trigger: 'Whenever you name recipes from this server in an answer, pass those same ones here.' It also implies, through 'URLs you are already holding,' that this is not a discovery or search tool, separating it from the siblings. It lacks an explicit when-not-to-use statement naming alternative search tools, but the core usage context is clearly stated.

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