investigate_slow_screen

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

There are no annotations, so the description carries the full burden. It discloses the core behaviors: profiling JS and React, optional tap, fetching component names, and returning a diagnosis with artifact paths. The 'one-shot' hint implies it manages the entire start/stop lifecycle internally, which is useful context. However, it does not mention side effects like whether existing profiles are cleared or if artifacts are left behind, but overall it gives a solid behavioral overview.

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, front-loaded with 'PREFERRED' and the core action, and every sentence is informative. It avoids repetition and packs the key details (profiling scope, optional tap, output, and usage context) into a compact format.

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 tool is complex (5 parameters, no output schema, no annotations) but the description provides a high-level summary of the workflow and return value. It lacks details on parameter semantics, the exact format of the 'rule-based diagnosis', and artifact path structure. Given the absence of structured schemas, the description is adequate but not fully complete.

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 no parameter descriptions (0% coverage), so the description must compensate. The only parameter hint is 'optional tap' which vaguely covers tapLabel/preferCdpTap/targetId, but the other parameters (platform, settleMs) are not explained at all. The description adds minimal semantic value beyond the schema's parameter names.

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 a specific action: 'profile JS + React around an optional tap, fetch component names, return rule-based diagnosis + artifact paths.' It clearly identifies the tool as a one-shot combined profiling and diagnostic tool, distinguishing it from the many individual profiling/tapping sibling tools. The phrase 'PREFERRED one-shot' further emphasizes its unique role.

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 explicitly tells when to use this tool: 'Use this instead of chaining start/stop/tap tools when asking why a screen is slow.' It mentions the alternative (chaining start/stop/tap tools) and the specific scenario (slow screen). This is clear, direct guidance that differentiates it from the siblings.

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