Take bounded heap snapshot

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

With no annotations, the description carries the burden of behavioral disclosure and does well by revealing two important traits: it writes a private local artifact and it fails rather than returning an incomplete snapshot on buffer truncation. It does not cover authorization, runtime impact, or artifact lifecycle, but the provided details are meaningful and non-obvious.

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 concise sentences deliver the core behavior and a critical failure mode with no filler. Front-loaded purpose and immediate follow-up on failure handling make it easy to scan.

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?

The tool has three parameters, no output schema, and no annotations, so the description must compensate. It explains the core purpose and failure behavior but omits parameter semantics, return value/artifact details, and usage context. This is insufficient for an agent to confidently invoke the tool.

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%, and the description does not explain any of the three parameters (sessionId, targetSessionId, captureNumericValue). The agent cannot infer the role of these parameters from the description, making correct invocation difficult.

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 uses a specific verb ('Capture') and a clear resource ('HeapProfiler snapshot chunks from Raw events') plus outcome ('write a private local artifact'). It distinguishes itself from sibling profiling tools like profiler_cpu and profiler_heap_sampling by focusing on snapshot chunks and the local artifact.

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 does not state when to use this tool versus alternatives such as profiler_heap_sampling, performance_trace, or performance_get_metrics. There is no mention of prerequisites, exclusions, or a preferred context beyond the inherent implication of the name.

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