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

The annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavioral context beyond them: it does not perform measurements and does not compute a blanket SEO score, which prevents the agent from over-interpreting results. It still says nothing about how thresholds or findings are returned.

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?

Three short sentences, front-loaded with the core split (lab vs. field) before the check and the negative scope statement. Every sentence carries information; only the SEO-score disclaimer is somewhat defensive, but it earns its place as a scope boundary.

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?

This is a complex tool with 10 parameters, nested objects and no output schema, so the description has to do more work. It covers the analytical behavior well but never describes the shape of the result (verdicts per metric? per resource?) or the role of the period/percentile fields, leaving the agent to infer how to assemble a full call.

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 carry the load. It does explain the meaning of several key inputs — kind (lab vs. field), device (per-device evaluation), metrics (LCP/INP/CLS p75) and resources (large resources in the trace) — but leaves source, observed_at, percentile, period_start and period_end entirely unexplained.

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 names a specific verb and object: it splits lab vs. field data, checks supplied p75 field values per device against LCP/INP/CLS thresholds, and lists large resources in the supplied trace. That is concrete and distinguishes it from measurement tools via 'Führt keine Messung aus'. It does not explicitly differentiate itself from the closest sibling, analyze_performance_export, so it stops short of a 5.

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?

Usage is implied rather than stated: the repeated word 'geliefert' signals the tool only evaluates data the caller already holds, and 'Führt keine Messung aus' steers the agent away from audit/measurement tools. However, no alternative is named (e.g. analyze_performance_export or audit_website), and no prerequisites or when-not conditions are given explicitly.

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