start_debugger

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

With no annotations provided, the description must disclose behavioral details. It does not state that starting the debugger may suspend or modify the current state, whether it requires specific permissions, or what happens if the debugger is already active. The output schema exists but is not referenced to explain return values.

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 sentence of 14 words, front-loading the core action. Every word is necessary and there is no redundant information.

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 presence of an output schema and the complexity of starting a debugger (which may have failure modes or state requirements), the description is too sparse. It lacks information about return values (likely a success indicator or debugger handle), error conditions, or state changes.

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 says parameters are optional (args, path) but does not explain their format, purpose, or default behavior. This adds minimal value over the schema's property names and defaults.

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 starts a debugger for the currently loaded binary, which is a specific verb+resource. It is distinct from sibling tools like 'set_breakpoint' or 'step_into' that operate within the debugger lifecycle.

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 mentions optional parameters (command-line arguments and binary path) but does not give guidance on when to use this tool vs alternatives like 'suspend_debugger' or 'exit_debugger'. It does not mention prerequisites (e.g., binary must be loaded) or that the debugger must not already be running.

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