plan_capture

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds context by explicitly stating 'This tool never executes the workload,' which clarifies the non-execution guarantee beyond the abstract hints. It also explains the behavioral implication of auto mode regarding 'no enforced descendant containment,' adding useful semantic detail without contradicting annotations.

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 relatively brief but contains a potentially confusing sentence: 'The default auto mode runs the declared workload directly in the local environment' could be misread as the tool executing the workload, even though the final sentence clarifies it never executes. The structure is acceptable but could be tightened for clarity.

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 complex input schema (nested objects like TorchProfilerCaptureOptions and ComputeSanitizerCaptureOptions) and 8 parameters, the description only covers the core purpose and capture_mode. It does not explain prerequisites like 'current capture,' preflight modes, or how external_context is used. Though an output schema exists, it does not mitigate the lack of input parameter guidance.

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 only 38%, so the description must compensate. It does add guidance for capture_mode (auto/managed/trusted_local), but it ignores other key parameters such as preflight_mode, external_context, torch_profiler_options, and compute_sanitizer_options. For a tool with 8 parameters, this partial coverage leaves the agent under-informed about most inputs.

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 opens with a specific verb+resource: 'Bind one current capture without running it,' which clearly distinguishes it from execution tools like execute_capture_plan. The closing line 'This tool never executes the workload' reinforces the non-execution purpose, making it unambiguous.

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 provides explicit guidance on when to use different capture_mode values: 'Use managed only when the project policy explicitly requires containment, and use trusted_local to request the same direct local execution explicitly.' However, it does not directly contrast plan_capture with sibling tools or state prerequisites, so the guidance is limited to parameter selection rather than tool selection.

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