recommend

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

Annotations already indicate a safe read-only and non-destructive operation, so the description does not need to restate that. It usefully adds that the tool invokes Qdrant's native recommendation API and explains the positive/negative example semantics. More behavioral detail such as pagination or ordering is not described, but that is acceptable given the annotations.

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 only two sentences: one states exactly what the tool does, and the second provides the main selection condition for when to use it. It is lean and front-loaded, with only a slight redundancy between 'recommends points' and 'point at examples'.

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 4-parameter read-only tool with an output schema and safe annotations, the description provides sufficient context: it names the mechanism, the expected input style, and the core positive/negative semantics. It stops short of exhaustively covering edge cases or alternative sibling routing, but the main operating context is fully represented.

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 0%, so the description has to carry meaning for the parameters. It gives good semantics for 'positive' as examples of what the user wants more of and 'negative' as what they want less of, and it establishes that these are point IDs. However, it does not explain the 'limit' or the 'collection' parameter, relying on the schema titles and defaults for those.

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 Recommends points using positive and negative example point IDs via Qdrant's native recommendation API. It distinguishes this from text-query search by explicitly noting the trigger intent is pointing at examples, not phrasing a query.

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 gives a clear when-to-use condition: 'Use this when the user can point at examples of what they want more or less of.' It also implies when not to use it by saying 'rather than phrasing a text query', but it does not name sibling alternatives explicitly.

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