neuron_perf_snapshot

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

With no annotations provided, the description carries the full disclosure burden. It does disclose the scope of captured data in detail, which is genuine behavioral transparency about the output. However, it omits side effects (e.g., whether it injects JS into the page), measurement semantics (e.g., whether LCP/CLS measurement requires a navigation or reload), and whether the operation is read-only — material gaps for a profiling tool.

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?

A single sentence with the action verb front-loaded, followed by a dash and a compact enumeration of the captured metrics. Every clause carries information and there is zero filler or repetition of schema content.

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 thoroughly answers 'what will I get back' by enumerating the snapshot contents, which is the core question given no output schema. It falls short on side-effect disclosure, prerequisites (e.g., a loaded/settled page), and usage boundaries versus performance-adjacent siblings — real gaps for a tool with no annotations to back it up.

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% — tabId is documented as 'Chrome tab ID to profile' — so the schema owns parameter documentation. The tool description adds no parameter-specific detail beyond contextualizing what 'profile' means via the metric list, which matches the baseline of 3 for high schema coverage.

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 pairs a specific verb ('Capture') with a specific resource ('performance snapshot') and enumerates eight distinct metric categories (LCP, CLS, TTFB, FCP, resource breakdown, slow resources, blocking scripts, memory, long tasks). This inventory functionally separates it from close siblings like neuron_waterfall and neuron_session_diagnostics, which are not all-in-one performance captures.

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 metric list strongly implies the tool is the go-to for holistic performance profiling, so usage context is inferable. However, the description never states when not to use it or names an alternative such as neuron_waterfall for request-level timing or neuron_get_requests for traffic data, leaving the boundary to the agent's judgment.

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