restart_debugging

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

With no annotations, the description carries the full burden and does well: it discloses the destructive terminate step, automatic breakpoint re-application, get_output buffer reset ('read from since=0'), and the readiness-window return contract ('running' with pending:true). It omits permission/auth requirements, but behavioral coverage is otherwise strong.

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?

Front-loaded with the core action, then constraints, then return contract. Every sentence earns its place — breakpoints, buffer reset, valid states, and exclusions are each distinct operational facts, not padding.

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?

No output schema exists, but the description explains the return shape ('Answers like start_debugging... running with pending:true'), which is what an agent needs to interpret the result. Combined with the state and exclusion rules, it is complete enough to call correctly; only sessionId semantics are unaddressed.

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?

One parameter (sessionId) with 0% schema description coverage, so the description must compensate and largely does not — sessionId semantics (which kind of session, relation to create/attach) are left to inference. The reference to sessions via exclusions implies context but adds no field-level meaning. Baseline 3 for a single obvious param.

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?

States a specific verb+resource ('Restart the debuggee') and immediately scopes it as 'terminate the current program... and relaunch it with the same configuration as the last start_debugging.' This distinguishes it from siblings like start_debugging (fresh config), continue_execution (resume), and attach_to_process (attach, which it explicitly excludes).

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?

Gives explicit when-it-works ('Works while running, paused, or after the program has exited') and when-not ('Not available for attach sessions or sessions never launched'). The reader knows exactly when to reach for this tool versus start_debugging or continue_execution.

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