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

No annotations are provided, so the description carries the full burden — and it actively misleads. It claims a live count of current HN front-page stories, implying real network access, while the schema signals the opposite: parameters like 'feed' (titles discarded) and 'path' (no disk access) reveal this is a pure shape check with no fetching. The description discloses none of this and sets false expectations about observable behavior.

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?

Two short sentences, front-loaded with the intended action. 'Titles discarded' echoes the schema's discard semantics efficiently. The brevity itself is not a flaw, though it is so short that it omits the essential behavioral context.

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?

With 9 optional parameters, zero annotations, no output schema, and no explanation of how the count is produced or returned, the description is grossly incomplete. An agent cannot tell which parameter to pass for a count, whether the result is a number, or what happens when inputs are discarded — everything an agent needs is missing.

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 even though the description adds nothing about parameters. The schema descriptions are individually clear about each field, but they do not connect any parameter to producing an HN count — a semantic gap the description fails to bridge, since it names no parameter that yields the story count.

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 a specific action ('Count current Hacker News front-page stories') but this purpose is contradicted by the schema, where every parameter is described as 'discarded after the shape check', 'discarded after the call', or otherwise discarded. The tool is structured as a shape-validation stub (mirroring sibling tools like domain-shape, github-repo-shape), yet the description promises a real network fetch and count that the parameter list gives no mechanism to perform.

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 offers zero guidance on when to invoke this tool versus any of its 28 siblings, none of which would plausibly produce an HN story count. No context, no exclusions, no alternatives are given — an agent is left with no basis to select it correctly.

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