Recipe Signal

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds meaningful context: the slugs must be 'known' (pre-existing) and that the comparison uses specific metadata fields. It repeats the telemetry requirement already present in the schema, but that repetition is minor. No contradiction with annotations exists.

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: the first states the core purpose and scope, and the second provides essential telemetry usage. There is no fluff, and key information (count range, metadata fields, telemetry rules) is front-loaded. Every sentence 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?

The tool has a rich output schema and strong annotations, so the description does not need to explain return values or safety. It covers the core input semantics and telemetry requirements. However, it does not mention how the comparison is returned or any handling of invalid slugss—though 'known' hints at validity. Given the presence of output schema and annotations, this is adequate but not exhaustive, so a 4 is appropriate.

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 schema describes the 'slugs' array constraints but gives no semantic meaning for the slugs; the description adds that they are 'Recipe Signal recipe slugs' and that they must be 'known', which directly clarifies what values are acceptable. The telemetry parameter is already well-described in the schema, so the description's focus on slugs fills the main gap. With schema coverage at 50%, the description compensates effectively.

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 ('Compare'), a specific resource ('two to five known Recipe Signal recipe slugs'), and the comparison dimensions ('published time, rating, rating volume, yield, cuisine, and publisher metadata'). This clearly distinguishes it from siblings: get_recipe fetches a single recipe, search_recipes finds recipes, and get_comparison_guide provides guidance rather than direct comparison.

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 clarifies when to use this tool: when you have two to five known Recipe Signal slugs to compare. It does not explicitly name alternative tools or provide exclusion criteria, but the 'known slugs' constraint gives a clear prerequisite. The telemetry instruction is useful invocation guidance but not about choosing among alternatives, so this is a 4 rather than 5.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond those hints: data is human-reviewed, the response contains criteria/editorial notes/source URLs, and telemetry must follow specific rules (agent_thinking on every call, user_intent only on first call after a new message). 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?

The description is organized into two purposeful paragraphs: the first states the tool's function and output contents, the second gives necessary telemetry usage instructions. There is no filler, though the telemetry paragraph is somewhat redundant with the schema descriptions; however, its placement in the description ensures the agent won't miss it.

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, the description explains what the response includes (criteria, editorial notes, original source URLs). Annotations cover safety, and the schema covers telemetry format. The only real gap is explicit guidance on when to choose this tool over compare_recipes, but the fixed recipe list and 'human-reviewed' wording largely clarify its narrow scope.

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 schema gives strong descriptions for telemetry fields but leaves 'slug' with no description. The description compensates by enumerating the human-readable dishes that map to the slug enum, and it clarifies telemetry inclusion timing with concrete rules. This meaningfully adds to the schema, especially given the 50% schema coverage.

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 the specific verb 'Retrieve' and clearly names the resource: a human-reviewed Recipe Signal comparison for fixed dishes (kadhi chawal, rajma chawal, idli sambar, pizza), with return content. This distinguishes it from siblings like compare_recipes by emphasizing the editorial/reviewed nature and the closed recipe set.

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 implies when to use the tool: when a human-reviewed editorial comparison for one of the four listed dishes is needed. However, it does not explicitly state when to prefer this over compare_recipes or search_recipes, nor does it mention any alternatives or exclusions. The telemetry instructions are operational, not tool-selection 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?

Beyond the read-only/idempotent annotations, the description adds meaningful behavioral context: it reveals what the response contains (facts and the publisher URL, not recipe text) and provides explicit operational guidance about telemetry fields (agent_thinking on every call, user_intent only on the first call after a user message). This exceeds what the annotations alone communicate.

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 compact and front-loaded: the first sentence states purpose, the second defines the return scope, and the third/fourth give telemetry instructions. There is no redundancy; every clause adds distinct value.

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 single-record fetch tool with an output schema and safety annotations, the description covers the essential decision-to-call information, return contents, and the telemetry contract. No meaningful gaps remain for an AI agent to select and invoke the tool correctly.

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 only 50%, so the description compensates by defining 'slug' as a stable Recipe Signal slug (the schema only has length constraints). It also clarifies the telemetry parameter's usage (when to include user_intent vs agent_thinking), which adds meaning beyond the schema's property descriptions.

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 a specific verb ('Retrieve') with a clear resource ('one attributed recipe metadata record') and a specific lookup key ('stable Recipe Signal slug'). It also states what the tool returns (facts and original publisher URL, not copied instructions), which clearly differentiates it from siblings like search_recipes and compare_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 clearly implies when to use this tool: when you have a stable Recipe Signal slug and need a single metadata record. It also gives an exclusion ('not copied recipe instructions'), but it does not explicitly name alternatives or say when not to use it, so it stops short of a 5.

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 indicate this is read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations by specifying telemetry requirements: always include agent_thinking, and only include user_intent on the first call after a user message. This is a concrete instruction that affects how the agent should invoke the tool, which is behaviorally transparent.

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 concise and front-loaded with purpose. The second paragraph about telemetry is somewhat redundant with the schema's telemetry description, but it serves to reinforce critical behavior. Overall, it is well-structured without unnecessary fluff, earning a solid score.

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 tool's complexity (7 parameters, nested telemetry object, output schema present), the description is complete. It covers what the tool does, when to use it, and critical telemetry invocation rules. An output schema exists, so return values need not be explained, and the description provides enough context for correct 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?

Schema coverage is high at 86%, so the baseline is 3. The description adds meaning by mapping the conceptual filters (dish, cuisine, category, publisher, max time) to the parameter usage, and it clarifies the telemetry parameter semantics with explicit instructions on when to include user_intent. This compensates for any gaps and adds value beyond the schema.

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 the tool's function: 'Search attributed recipe metadata by dish, cuisine, category, publisher, and maximum total time.' It uses a specific verb and identifies the resource. It also distinguishes itself from a sibling by instructing to use this before get_recipe when the exact slug is unknown, making the purpose unmistakable.

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 usage guidance: 'Use this before get_recipe when the exact slug is unknown.' This tells the agent when to use the tool (searching when the specific recipe identifier is not known) and when not to use it (when the slug is known, implying get_recipe should be used instead). It also gives an alternative tool name, which meets the 'alternatives' criterion.

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