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

With the readOnlyHint annotation covering safety, the description adds meaningful behavioral context by explaining the use of embedding similarity, recency filtering, and the nature of the output. This enriches understanding beyond the annotation alone, without contradiction.

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 a single, front-loaded sentence that packs in the core concept ('Semantic more like this'), input requirements, and output contents without any fluff. Every part earns its place.

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?

Given the tool's low complexity, existing output schema, readOnly annotation, and a clear description covering input source and expected output, there are no significant gaps. The description sufficiently orients an agent on when and how to invoke 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?

The schema fully documents both parameters (id and limit). The description adds extra meaning by clarifying that the id originates from specific source tools (get_new_since, search_news, or the feed), which complements the schema's generic 'UUID of an item from a previous result'.

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 returns semantically similar items via 'semantic more like this' given an item ID, and explicitly lists the output fields (titles, sources, similarity scores, links). It distinguishes itself from sibling tools by focusing on item similarity rather than new/search/regional signals.

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 conveys when to use it by specifying that the input is an item ID from get_new_since, search_news, or the feed, implying it is for follow-up exploration after retrieving an item. It does not explicitly name alternatives, but the context and sibling list make the usage scenario clear.

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