detect_performance_anomalies

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

With no annotations provided, the description carries full behavioral burden and does so thoroughly. It discloses the specific thresholds (gaps >50ms, actions >500ms), the types of analysis (frame timestamps, concurrent network requests, monotonic duration checks), and the output format (ranked list with suspected_cause). This gives an agent a complete understanding of what the tool will do.

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 tightly structured into three sentences: what it detects, how it analyzes, and what it returns with a clear purpose. Every clause adds information without redundancy. It is dense but not verbose, earning a high score for conciseness and logical organization.

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 tool's complexity and lack of output schema, the description sufficiently covers input (trace_path implied), processing methods, and return type (ranked anomalies with suspected_cause). It omits edge cases like invalid trace paths or behavior when no anomalies are found, but these are not critical for an agent to use the tool effectively. The description is complete enough for a tool of this complexity.

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%, so the baseline is 3. The description adds semantic value by explaining how the frame_drop_threshold_ms and slow_action_threshold_ms parameters relate to the analysis logic (e.g., 'gaps > 50ms' and 'actions longer than 500ms'). It does not explicitly name the parameters but provides behavioral context beyond the schema descriptions.

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 states the tool's purpose: detecting Long Tasks and frame drops that cause Playwright timeouts. It specifies the exact analysis performed (screencast-frame timestamps, main-thread blocking, slow actions, concurrent network requests, monotonic action durations) and distinguishes itself from sibling tools like analyze_race_conditions by focusing on performance-based timeout causes.

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 implicit usage guidance by stating the tool helps distinguish blocked main thread, network saturation, or navigation timeout 'without blaming a missing element.' This suggests using it when a timeout may be performance-related rather than due to a missing element, but it does not explicitly name alternatives or provide direct when-to-use/when-not-to-use exclusions.

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