profiler

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context by clarifying that operations affect only the current execution context and that no persistent changes are made, reinforcing the read-only nature without 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?

The description is concise and well-structured, listing actions with brief explanations and ending with a crucial limitation. Each sentence contributes useful information without redundancy, making it easy for an agent to parse quickly.

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 description adequately covers all actions and the types of data collected (FPS, memory, draw calls, p99 percentile, trends, etc.) for a tool with several parameters and no output schema. It could elaborate on the return format of get_data, but the current level is sufficient for selecting and invoking the tool correctly.

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 100%, with each parameter thoroughly documented including enums and defaults. The description's mention of multi-dimensional sampling and frame-level data aligns with the schema but does not add significant extra meaning, so the baseline score of 3 is appropriate.

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 identifies the tool as a '性能分析工具' (performance analysis tool) and enumerates specific actions (snapshot, start/stop, get_data, get_active_processes, get_signal_connections) with explicit purposes. This distinguishes it from sibling tools by focusing on runtime profiling and scene introspection.

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 states that operations are runtime-only and affect only the current execution context, explicitly noting that persistence requires editing .tscn files. This provides a clear when-not-to-use condition, though it does not explicitly name alternative tools for persistent changes.

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