query_qdrant

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

With no annotations, the description carries the full disclosure burden and does well: it states the query runs against Qdrant only, that nothing is embedded remotely and no model is called, that filters are an error (not silently ignored) for patterns, that results are best-match-first, and that scores are deliberately not returned. Missing are behaviors like empty-result handling and the 1-50 limit boundary, keeping it from 5.

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?

Front-loaded with the core action in the first sentence, then structured per-collection, then a return-shape note. The backtick-heavy prose is slightly ornate but every sentence carries information; nothing is filler.

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 search tool with an output schema present, this is complete: collection semantics, filter applicability, error behavior, run-time dependencies, and result ordering/typing are all covered without re-explaining the output schema.

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 coverage is 50%, so the description must compensate, and it does by enumerating the filter dimensions ('publication window, source, reduced value or master number') and, more importantly, by scoping filters to collection='news' only. It does not discuss the limit or query parameters, so it is not fully covering the gap.

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?

States a specific verb+resource ('Search the stored news or patterns by meaning') and splits the two target collections so each has a distinct meaning. An agent can tell it apart from find_patterns and fetch_news without opening the schema.

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?

Gives explicit per-collection usage: news supports optional payload filters with enumerated dimensions, patterns takes none and rejects them as an error rather than ignoring them. It stops short of naming or routing against the similarly-named sibling tools (find_patterns, check_master_numbers), so 4 rather than 5.

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