start_profiling

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Start profiling' implies an ongoing monitoring operation, but the description doesn't reveal what profiling entails (e.g., collecting performance metrics, tracking renders), whether it requires specific conditions (e.g., a connected React app), what resources it consumes, or how to stop it. This leaves significant behavioral gaps for a tool that initiates a monitoring process.

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 a single, focused sentence with zero wasted words. It's front-loaded with the core action and target, making it immediately understandable. Every word earns its place by conveying essential information about what the tool does.

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 complexity of starting a profiling operation with no annotations and no output schema, the description is insufficient. It doesn't explain what 'profiling' means in this context, what data will be collected, how to access results (presumably via 'get_profiling_data'), or any side effects. For a tool that initiates monitoring in a development/debugging environment, more context is needed to use it effectively.

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 input schema has 100% description coverage, with both parameters clearly documented ('recordTimeline' and 'recordChangeDescriptions'). The description adds no parameter information beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without adding value. The parameters control what data gets recorded during profiling, which is adequately covered in the schema.

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 'Start profiling React renders' clearly states the action (start profiling) and target (React renders), providing a specific verb+resource combination. However, it doesn't differentiate from its sibling 'stop_profiling' beyond the obvious start/stop distinction, nor does it explain what 'profiling' entails compared to other performance-related tools in the list.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a React app running), when profiling is appropriate (e.g., during performance debugging), or how it relates to sibling tools like 'get_profiling_data' or 'stop_profiling'. The agent must infer usage from the name alone.

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