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

Annotations already cover safety (readOnly, idempotent, openWorld=false, non-destructive), yet the description adds real behavioral context: determinism tied to rule version, the not_tested convention for missing inputs, and the caveat that a DOM snapshot is not a browser test. These are non-obvious semantics an agent could not derive from the annotations.

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 tight sentences with the core capability front-loaded and no filler. The determinism and not_tested clauses each add distinct information rather than restating the title.

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?

For a 14-parameter tool with deep nesting, zero schema descriptions and no output schema, the description is too thin: the largest input ('expected_business') and the results shape ('Befunde') are never characterized. An agent can grasp the concept but cannot confidently populate most of the schema from this text alone.

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% across 14 parameters, including large nested objects, so the description carries the full burden. It gestures at the snapshot families (HTTP, robots, sitemap, DOM/rendered_html) but explains nothing about expected_business, paid_link_urls, target_results, redirect_chain, related_pages, or observed_at, leaving most inputs semantically opaque.

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 gives a specific verb ('Prüft') and resource ('geliefertes HTML und optionale HTTP-/robots-/Sitemap-/DOM-Snapshots') and pins the mode as 'ohne Netzwerkzugriff', which separates it from network-fetching siblings like audit_website. It never names an alternative tool outright, so the differentiation is inferred rather than explicit.

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 offline framing ('ohne Netzwerkzugriff', 'geliefertes HTML') implies when to use it: when the caller already holds snapshots rather than a live URL. There is no explicit statement of when to prefer audit_website or the analyze_* siblings instead, so usage is only implied.

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