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

Annotations already declare read-only, idempotent, open-world and non-destructive behavior, so the safety profile is covered. The description still adds value beyond them: it discloses rank ordering ('in rank order'), that the front page is live, that comment threads are returned whole, and that every item links back to news.ycombinator.com—a useful output-shape hint. Missing are rate-limit or pagination notes, but those are largely encoded in the schema's max_items constraints.

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?

The definition is two sentences with no filler, front-loading the primary verb and resource before enumerating modes. The first sentence is a long compound that packs in every mode, which taxes readability slightly, but nothing is redundant or padding.

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 13-parameter, multi-mode tool with no output schema, the description covers the three behavioral families, ordering, and a return-value hint (links back to news.ycombinator.com). Full parameter semantics are delegated to the exceptionally complete schema, and the safety profile is delegated to annotations. It stops short of describing result structure for story_comments output, but is otherwise sufficient to invoke correctly.

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 coverage is 100%, with every one of the 13 parameters carrying a description that names its applicable mode and accepted values. The description restates the filter categories (date, points, comment count) but adds no syntax, defaults, or edge-case guidance beyond what the schema already says. Baseline 3 is correct when the schema does the heavy lifting.

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 specific verbs and resources: search stories and comments with date/points/comment filters, read the front page and top/best/new/ask/show lists in rank order, or read whole comment threads. This covers all modes of the tool and clearly distinguishes it from every sibling, none of which touch Hacker News. An agent can tell exactly what the tool does without opening the schema.

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 implicitly routes usage by enumerating behaviors—filters go with search, rank-ordered reading goes with the front-page/list modes, thread reading with comments—and the schema's mode description makes the mapping explicit. It doesn't state when NOT to use the tool or name a fallback (e.g., read_page for non-HN URLs), but with unrelated siblings there is little alternative confusion to resolve.

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