add_watchpoint

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

Annotations are absent, so the description carries the full burden. It discloses trigger conditions (watch_type values) but omits critical behaviors: whether the debugger must be active, if it halts execution on trigger, how to clear the watchpoint, side effects on debug state, or whether address is virtual/physical. Hardware watchpoints have resource limits (e.g., x86 has 4 debug registers) - this is unmentioned.

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, concise and front-loaded with the most critical info (what it does and what triggers it). No filler. Every sentence adds value given the context.

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?

Tool has a moderate number of parameters (3) and no output schema (despite the signal claim, it says 'has output schema: true' but none was provided in input). Given complexity (hardware watchpoint), the description should cover behavior on trigger, clearing mechanism, bounds (e.g., contiguous memory only), and debugger state dependency. It's incomplete for safe invocation.

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. It defines watch_type values ('write, read, execute') but doesn't explain size (bytes? granularity?), or address format (hex? decimal? 0x prefix?). No parameter semantics for size or address beyond the schema. The description adds value for watch_type but under-documents size and address.

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 sets a hardware watchpoint (data breakpoint) and specifies it triggers on memory access at an address. It distinguishes from siblings like set_breakpoint (software breakpoint) and delete_breakpoint. However, it could be more specific about the scope (e.g., process-wide vs thread-local) to fully differentiate.

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?

No guidance on when to use this tool vs alternatives like set_breakpoint, step_into, or read_debug_memory. It doesn't mention prerequisites (e.g., debugger must be running, address must be valid, or hardware support needed). Without usage context, an AI agent might misuse it.

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