hang_analyze

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

With no annotations, the description fully bears the burden of behavioral transparency. It clearly states that the tool auto-pauses if running, lists threads, fetches top frames, classifies blocking patterns, and leaves the session paused. No contradictions.

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 extremely concise with two sentences: the first states the purpose, the second explains the actions and side effect. No wasted words.

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, the description adequately sets expectations: lists threads, fetches frames, classifies blocking patterns, and leaves session paused. It provides enough context for an agent to understand what will happen, though output format is not detailed.

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 single optional parameter 'topFramesPerThread' is fully described in the input schema (Top frames per thread to fetch. Default 10). The description adds no extra detail beyond mentioning 'fetches the top frames of each', so baseline 3 due to high schema coverage.

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 diagnoses why an application appears stuck, with specific actions like auto-pausing, listing threads, fetching top frames, and classifying blocking patterns. It differentiates from sibling tools like threads_list and stacktrace_get by providing a comprehensive stuck-detection analysis.

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 usage when an application is stuck, but does not explicitly state when not to use it or mention alternative tools. The side effect of leaving the session paused is noted, but no comparison to siblings like debug_pause is provided.

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