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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description only needs to add context. It adds 'source-backed' as a quality of results and constrains the category set. It doesn't disclose beyond that (e.g., empty results, limit application), which is fine given the modest annotation coverage.

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?

One sentence, no filler, and the core verb and object appear first. The category list and lookup method are packed efficiently. It earns a high score, though it is not structured with an explicit alternative pointer.

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 two-parameter read-only list call, the description covers what the tool returns at a high level and the key input. It omits output details and limit semantics, but the absence of an output schema makes that less critical. The tool is adequately specifiable from the description plus annotations.

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?

Despite 0% schema coverage, the description clarifies the category parameter format ('name or slug') and lists the recognized categories, which adds real meaning. The optional limit parameter is left without textual explanation, relying on its self-evident schema range. Overall the description partially compensates for the schema's silence.

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 verb ('Find'), a resource ('articles'), and a scoping dimension ('category name or slug'). It also enumerates the allowed category domains, which distinguishes it from generic sibling search tools. The only shortfall is not explicitly naming a sibling to differentiate from, so it stops short of the fully explicit standard.

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 implies the tool should be used when the caller has a category in the listed domains, but it gives no explicit when-to-use versus alternatives like search_articles or latest_articles. There is no exclusion clause or pointer to a sibling for broader queries. This leaves the selection decision to inference.

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