PRENOTO Menu

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

The annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds the factual scope of the response, but 'Read-only' largely repeats the annotation and no further behavioral context is needed or provided.

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?

Two short sentences with the purpose and usage condition front-loaded. Every sentence carries useful information and there is 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 simple, parameterless informational tool with rich annotations and no output schema, the description covers what the tool does and when to use it. It could be slightly more complete only by hinting at response structure, but that is 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?

The tool has zero parameters, so there are no parameter semantics to explain. This meets the baseline for a parameterless tool, though the description does not need to add anything further here.

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 and resource: 'Return factual information about PRENOTO Menu,' and enumerates the returned topics (what it does, price, languages, features). It is clearly distinguishable from sibling tools in practice, but it does not explicitly differentiate itself from create_menu_preview or get_menu_format.

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 usage trigger: 'Use when the user asks what PRENOTO Menu is or how it works.' It does not name exclusions or explicitly compare against siblings, so it stops short of full alternative 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?

The description adds significant context beyond annotations, detailing crucial behavioral traits like data fidelity rules ('keep dish names and prices exactly as written'), translation capabilities, and the side effect of non-idempotency (retrying creates a new link). This manages user expectations well.

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 dense but highly efficient. Each sentence conveys a critical constraint or capability (e.g., input conversion, translation, or data integrity rules), ensuring that the length is warranted by the value delivered.

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 weak input schema, the description provides most of the necessary context regarding the creation process, data handling, and resulting product (JSON + private link). It defines the 'why' and 'how' of the data conversion and translation.

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?

With low schema coverage (33%), the description acts as a primary documentation source. It explains the purpose of the 'notes' field, the need for content accuracy ('never invent dishes'), and how the 'defaultLanguage' affects the output.

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 clear specific verb ('Use when the user asks to create'), the resource ('digital or QR menu'), and the output format (JSON). It distinguishes itself by defining the specific function as 'Create' rather than managing an existing menu.

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 clearly defines the use case (creating a digital menu for venues) and the intended input source (photo, PDF, or text). It sets boundaries by explicitly stating that images cannot be used as input, steering the agent away from unsupported use cases.

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, so the sentence 'Read-only; it does not create anything' largely restates structured data. It does add what the response contains (instructions, JSON format, example), which annotations cannot express, but nothing about size, caching, or whether the format is versioned.

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?

Two short sentences, front-loaded with the returned artifacts, with the safety note second and no filler. Every 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?

There is no output schema, so the description does the responsible work of naming the three things returned (instructions, format, example), which is enough for an agent to know it should call this before create_menu_preview. It only misses whether the format is authoritative or how large the payload is.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the schema fully covers the empty input with additionalProperties=false. Baseline for a no-parameter tool applies unmodified.

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?

States a specific verb and resource ('Return the step-by-step instructions, the JSON format and an example') and scopes it explicitly to create_menu_preview, which distinguishes it from about_prenoto_menu. An agent can tell exactly what this tool yields without opening the schema.

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 phrase 'for create_menu_preview' makes the usage context clear: fetch this before invoking the sibling that creates the preview. It lacks an explicit 'call this first' directive or any when-not guidance, so it is slightly short of full routing clarity.

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