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

Beyond readOnlyHint/openWorldHint, the description discloses the deterministic no-LLM behavior, the 15-page crawl cap, the metadata/visible-text sourcing of descriptions, and the auxiliary outputs (validation, Lighthouse status, excluded URLs with reasons). This materially shapes an agent's expectations about cost and output quality.

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 sentences with the main action front-loaded in the first. Each subsequent sentence adds a distinct fact: determinism, delivered outputs, and input flexibility. No filler or repetition of schema content beyond minimal reinforcement.

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 2-parameter tool with no output schema, the description covers input, process, determinism, and the main return components (validation, Lighthouse status, excluded-URL list). A minor gap is the absence of failure/edge-case behavior for unreachable domains or crawl exhaustion.

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 schema already documents accepted url formats and the maxPages range (3–25, default 15). The description adds only marginal reinforcement by echoing the 15-page cap and clarifying that a bare domain is acceptable input.

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 first sentence names a specific verb+resource: it crawls up to 15 public HTML pages of a domain and produces a finished llms.txt draft. The determinism qualifier ('kein Sprachmodell aufgerufen') further distinguishes it from a generic LLM-based generator and from the sibling validation/check tools.

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 establishes clear selection context: use this to generate an llms.txt draft from a domain, and the determinism note ('Beschreibungen stammen ausschließlich aus den Metadaten oder sichtbaren Texten') implicitly tells agents not to use it when LLM-generated descriptions are desired. However, siblings like validate_llms_txt or check_published_llms_txt are never named, so the when-not-to-use guidance is implied rather than explicit.

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