find_what_writes

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

No annotations are provided, so the description must fully disclose behavior. It mentions 'attach the debugger' implying a side effect, but does not detail prerequisites (e.g., process must be attached), destructiveness, or the exact nature of collected instructions. Insufficient for safe invocation.

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 sentences that front-load the action and provide an example. No wasted words, but could be slightly more structured.

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 no annotations, the description covers the basic purpose and parameters but omits critical context: return value format, prerequisite of an attached process, and potential side effects. It is adequate for a simple tool but not complete for safe autonomous use.

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 description clarifies that 'address' is a memory address and 'duration' is in seconds, which adds value beyond the schema's names and types. However, it does not specify the expected format for address (e.g., hex) or valid ranges for duration. With 0% schema coverage, more detail would be helpful.

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 finds instructions that write to a given address, with a concrete example (decrementing health). This distinguishes it from siblings like 'find_what_accesses' by focusing specifically on write operations.

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 it is for finding code that changes a value but does not explicitly state when not to use it or mention alternatives like 'find_what_accesses' for reads. Usage context is implied but lacks direct guidance.

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