analyze_performance

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the tool performs a 'Performance view' which implies a read-only analysis, but doesn't clarify whether it mutates state, whether rescanning is expensive, what 'avoid rescanning' means operationally, or what the return format looks like. The mention of 'avoid rescanning' hints at side effects but is vague about performance impacts or prerequisites.

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 two sentences and gets to the point efficiently. The first sentence states what the tool does and what it returns; the second gives parameter guidance. No wasted words, though it could be considered slightly under-specified given the absence of annotations.

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 0% parameter coverage, the description carries substantial burden. It does identify the analysis categories (method sizes, setState issues, animation leaks) and parameter preference (sessionId over path), which is helpful. However, for a 3-parameter tool with no other structured metadata, it leaves gaps around the limit parameter semantics, expected output shape, and how findings map to an actionable result.

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%, so the description must add meaning to the parameters. It does explain that sessionId and path are alternative inputs and recommends sessionId to avoid rescanning, which adds real semantic value. However, it provides no information about the 'limit' parameter (likely a cap on results), and doesn't describe how sessionId vs path interact or what the trade-offs are beyond 'avoid rescanning'.

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 states the tool performs a performance view from a review_project session or path, specifically listing build method sizes, setState issues, and animation controller leaks. It has a specific verb (analyze) and resource (performance), but among the many sibling 'analyze_*' tools (complexity, documentation, testing, dependencies, accessibility), it does not clearly differentiate itself beyond naming the performance domain, which is implied by the tool name itself.

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 clear usage context: it works on a review_project session or path, and explicitly recommends preferring sessionId 'to avoid rescanning'. This gives the agent actionable guidance on the better parameter choice. However, it doesn't explicitly say when NOT to use this tool versus alternatives like analyze_code_quality or analyze_complexity, or how it differs from those sibling analysis tools.

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