ARC-1

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It describes specific implementation details: 'uses the full scope-based Where-Used API returning detailed results with line numbers, snippets, and package info' and 'returns superclass, implemented interfaces, and direct subclasses via SEOMETAREL.' It also notes system compatibility issues: 'On older systems, the filter is ignored and all references are returned with a note.' This provides valuable context beyond basic functionality.

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 appropriately sized and front-loaded with the core purpose in the first sentence. Each subsequent sentence adds valuable information about specific actions and parameters. While slightly dense, there's minimal waste - every sentence contributes to understanding tool behavior or usage.

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 (8 parameters, no annotations, no output schema), the description does a good job covering behavioral aspects and usage patterns. It explains what different actions do, provides implementation details, and notes system compatibility. The main gap is lack of information about return values or error conditions, which would be helpful since there's no output schema.

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 100% schema description coverage, the baseline is 3. The description adds some value by explaining the optional objectType filter format ('slash format e.g., CLAS/OC, PROG/P') and clarifying the type+name alternative to uri for references. However, it doesn't provide significant additional parameter semantics beyond what's already documented in the comprehensive schema 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 clearly states the tool's purpose with specific verbs and resources: 'find definitions, references (where-used), code completion, and class hierarchy.' It explicitly distinguishes this navigation tool from potential siblings like SAPSearch by focusing on code navigation rather than general search, and provides concrete use cases like 'go to definition' and 'where is this used?'

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 clear context for when to use this tool through examples like 'Use for "go to definition", "where is this used?", "what does this class inherit?", and auto-complete.' However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools (e.g., when to use SAPSearch instead for broader searches). The guidance is implied rather than explicit about exclusions.

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