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

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds detail about return content (guide with syntax/examples, schema with JSON Schema) and context about being authoritative. However, it does not explain response structure or potential size, but given annotations, the added value is moderate.

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?

Four sentences are concise and front-loaded with the main purpose. Each sentence adds new, useful information without redundancy. The structure guides the agent from purpose to parameter usage to when to choose this tool.

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 no output schema and two parameters, the description covers tool purpose, parameter choices, and usage context. It could be more explicit about return structure for the guide format, but it suffices for a read-only reference tool. The sibling tool (render) is not mentioned, but the description implicitly distinguishes via purpose.

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% with both parameters having clear enum descriptions. The description largely repeats this information ('Use format=guide for...', 'Choose dashboard for...'). While it adds overall context, it does not significantly enhance parameter meaning beyond 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 retrieves the authoritative OpenUI Lang contract for UI authoring, contrasting it with the sibling tool (render) and specifying purpose: 'before creating a complex Nuwax UI'. The verb 'Get' is specific and the resource is well-defined.

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?

Provides explicit guidance on when to use ('before creating a complex Nuwax UI', 'instead of guessing syntax or searching local package files') and how to choose parameters (format and profile values with intended use cases). Alternative actions are implied but clear.

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 only indicate non-readOnly, non-destructive, etc. The description adds context about persistence (durable artifact, file write), update capability via artifactId reuse, and reference return. It also warns about reactive filter handling. Some specifics about return value are vague ('lightweight reference') but sufficient.

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 informative but somewhat verbose, with repeated emphasis on OpenUI Lang not being XML/HTML/JSX. It could be more concise while retaining essential guidance.

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 objects, output schema exists), the description covers core functionality, usage scenarios, and key constraints. It omits details on bindings and fallback but still provides enough for an AI agent to select and invoke correctly. The presence of an output schema reduces the need to explain return values.

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 43%, but the tool description adds significant meaning for key parameters like document.source (with syntax rules) and presentation.mode (inline vs sidecar). It also explains artifactId reuse. However, bindings and fallback parameters lack elaboration 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 creates or updates a durable OpenUI artifact, lists many trigger phrases (show, render, visualize, etc.), and specifies the file output (data/{artifactId}.openui.json). It also distinguishes from the sibling tool nuwax_get_openui_reference.

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 provides when to use (user requests to show/render/visualize etc.) and when not (call nuwax_get_openui_reference first for complex UI or uncertain signatures). Also gives syntax rules for OpenUI Lang.

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