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

With no annotations present, the description carries the full burden of behavioral disclosure. It reveals that the attitude is a 'keyword heuristic only' (not reliable for deep analysis), that results are 'raw evidence for host-side synthesis' (not a final answer), and that it is 'point-in-time' and 'not a durable trust score.' This gives the agent important expectations about the tool's limitations and output nature. It could add more about how the tool handles edge cases, but it is transparent about its core 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?

The description is three sentences, with the primary purpose stated upfront in the first sentence. Each sentence adds value: the first defines what it does, the second clarifies its role and adds a comparison to a sibling, and the third adds a usage caveat. There is no wasted text, and the structure is efficient and front-loaded.

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?

The description is fairly complete for a data-retrieval tool: it states purpose, limitations, and usage guidance. An output schema exists, so return values need not be explained. However, the lack of parameter semantics is a notable gap, and it does not distinguish itself from other HN-related siblings like hn_search or hn_tag_search, which may also return stories. Given the complexity of 4 parameters and the absence of schema descriptions, the description should provide more guidance on how the parameters shape the result.

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?

The input schema provides no parameter descriptions (schema coverage 0%), so the description must compensate. However, the description does not explain what 'limit', 'since', or 'until' do. While 'query' is self-evident from context, the other three parameters are undocumented. The phrase 'HN stories + counts' implies limit affects counts, but it is not explicitly stated. This is a significant gap for an agent attempting to invoke the tool correctly.

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 clearly states the tool's function: 'Point-in-time community signal: HN stories + light attitude hint + counts.' It specifies the resource (HN stories) and what it returns (attitude hint and counts). It also distinguishes itself from hn_attitude by clarifying that this is a keyword heuristic, not fine-grained stance analysis, which helps differentiate from a key sibling.

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?

Explicit guidance is provided: 'call hn_attitude for finer stance work' gives a direct alternative for a different need. 'Re-query when asking again (not a durable trust score)' tells the agent when to re-use the tool and cautions against treating results as persistent. This covers both when to use and when not to use, with a clear fallback.

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