Generate /llms.txt & Lighthouse 13.5 ai-catalog.json Manifests

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description still adds useful context beyond that: no API key required, remote servers are not modified, and the output is 'ready-to-save' (i.e., synthesized content rather than a write). It does not describe return format or caching, so it is not exhaustive.

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?

Four sentences, purpose front-loaded in the first, with usage and exclusion rules following. Information-dense with no filler, though the opening sentence carrying three artifact types is heavy and slightly harder to scan than a bulleted form.

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 single-param, read-only synthesis tool with strong annotation coverage, the description covers what is produced, when to use it, alternatives, and auth requirements. The only gap is what the caller receives (raw file contents vs. counts/paths), though 'ready-to-save' partially implies this and no output schema exists to cover it.

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?

Only one parameter (domain) and schema coverage is 100%, with the schema itself documenting accepted forms ('example.com' or 'https://example.com'). The description adds 'from a live domain', reinforcing that it is fetched live rather than passed as content, but adds no syntax beyond the schema. Baseline 3 for high coverage applies.

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?

Names a specific verb (compiles) and concrete resources: /llms.txt, Lighthouse 13.5 /.well-known/ai-catalog.json (ARD 1.0), plus HTML head and robots.txt snippets. The sibling differentiation is explicit (extract_byte0_markdown for scraping, audit_ai_readiness as the upstream detector).

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?

States exactly when to use it ('remediate missing discovery manifests identified by audit_ai_readiness') and when not to ('general web scraping (use extract_byte0_markdown instead)'). Both the trigger condition and the alternative tool are named, leaving nothing to inference.

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