debugger_exception_info

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. Beyond that, the description adds nothing: it does not say the call fails unless the thread is stopped, nor that the StopToken generation expires on resume, which is the main behavioral trap for this tool. "Inspect" is consistent with the read-only annotation, so no contradiction.

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?

A single efficient sentence with no wasted wording, but its brevity comes at the cost of under-specification rather than genuine density. Nothing beyond the tool name is front-loaded.

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?

With 3 required parameters, nested reference objects, and non-obvious staleness semantics around the stop token, the description should carry more weight. An output schema exists so return values need not be explained, but the preconditions for a successful call are absent.

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 reported as 0% at the top level; only the nested StopToken/Timeout defs carry any prose. The description contributes zero meaning about session_id, thread, stop, or timeout, leaving the agent to reverse-engineer the snapshot/generation coupling from the $defs alone.

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 verb ("Inspect") and resource ("exception details"), and scopes it to "the current stopped thread". That is enough to know roughly what it returns, but it does not distinguish it from nearby siblings like debugger_stack, debugger_scopes, or debugger_variables, and calling it "current" is imprecise since the caller must explicitly supply a thread reference and stop token.

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 when-to-use guidance, no prerequisites (thread must be stopped at an exception), and no comparison to alternatives such as debugger_stack or debugger_wait. The agent must infer usage entirely from the name.

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