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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered; the description adds substantial context beyond them. It discloses the reporting side effects (shareable reportUrl retained 30 days, null for tools that keep none), the error format (one plain sentence), and an explicit data-recording boundary (domain and path only, never query string, IP, or page text). Those are exactly the details an agent cannot get from 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?

Purpose and trigger are front-loaded in the first two sentences, with return shape and recording policy following. It is dense rather than padded, but the return-shape sentence ('result has llmsTxt..., saveAs..., links, sitemapUrls and existingLlmsTxt') and the 'details below' phrasing overlap slightly with the JSON return sentence.

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?

There is no output schema, so the description carries the full burden of explaining returns, and it does: both the top-level envelope (summary, reportUrl, result) and the result fields are enumerated, including what existingLlmsTxt means. Combined with the usage condition and edit-before-publish caveat, an agent has everything needed to call this and interpret the response.

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% and both parameters are documented there, including the origin-only behavior of url and the 5-50 range of maxLinks, so the baseline is 3. The description reinforces that content comes 'from its home page and sitemap' and that links are grouped by section, but adds no format or edge-case detail beyond the schema.

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?

States a specific verb (drafts) and resource (a starter llms.txt) and immediately spells out what the artifact contains: an H1 site name, description as summary, and main pages grouped by section. That resource-level specificity separates it from siblings like draft_json_ld and draft_ai_crawler_policy without needing to name them.

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?

Gives an explicit triggering condition: 'Use it when the site has no llms.txt or a broken one,' which is actionable and non-obvious. It also warns that the person should edit the result before publishing. It stops short of naming alternatives such as check_site_files (for diagnosing an existing file) or draft_ai_crawler_policy, so the selection boundary is inferred rather than stated.

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