analyze_performance

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

With no annotations provided, the description carries the full burden of disclosing behavior. It states the analysis is 'static', hinting at non-destructive read-only behavior, but it does not disclose whether it modifies any state, what inputs are required, or what the output format is. The description is too terse to provide adequate behavioral transparency.

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 sentence with minimal waste, and the key purpose is front-loaded. However, the '[mode: real]' prefix adds a small amount of irrelevant metadata that doesn't help comprehension. Overall, it's concise but not a model of informative brevity.

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?

With no annotations, no output schema, and only two parameters, the description still fails to convey essential operational details such as expected inputs, return value, or usage context. The tool is an analyzer, but an agent cannot determine what to pass or what to expect back, making the description insufficient for reliable invocation.

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 schema has 0% description coverage, and the description does not mention projectPath or platform at all. It provides no hints about how these parameters affect the analysis, leaving the agent to infer from the schema alone. The described focus areas (rendering, computation, bundle) give vague context but no concrete parameter mapping.

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 performing static performance analysis, specifying three focus areas (rendering, computation, bundle). This distinguishes it from sibling analysis tools like analyze_app_structure or detect_memory_leaks, though it doesn't name them explicitly. The verb-resource pairing is specific and clear.

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 word 'static' implies using this tool when a non-runtime analysis is needed, contrasting with dynamic tools like run_simulation or run_stress_test. However, it provides no explicit when-to-use guidance or alternatives, leaving usage to be inferred from the term 'static' alone.

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