cross_reference_address

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

The readOnlyHint annotation is supported by the description's lack of mutation language. The description adds the classification behavior (read/write/coil/set/reset) which gives the user a sense of the output categories, going beyond a simple 'lists references' statement. It doesn't describe auth or rate limits, but for a read-only tool this is 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 a single, well-structured sentence that says everything it needs to without waste. It's appropriately sized for the complexity of the 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?

For a read-only search tool with an output schema, the description is largely complete. It covers the core function and adds value by noting the classification output. It doesn't mention edge cases like what happens with invalid addresses, but that's likely covered elsewhere. Overall, a solid, complete description.

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 0%, so the description must compensate. The description clarifies what 'address' refers to and what kind of analysis is performed on it (classifying references). However, it doesn't explicitly document the semantics of 'project_id' beyond the schema, nor describe the return format in detail, leaving some room for interpretation.

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 ('Find every program reference to an address') and adds the classification dimensions ('read/write/coil/set/reset'), clearly distinguishing it from sibling tools. It's a complete, specific statement of the tool's function.

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 states what the tool does, implying when to use it (when you need to find references to an address). However, it doesn't explicitly mention when not to use it or name alternatives like search_program or get_program_context, though the specificity makes the use case clear.

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