search_rag

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the two-tier result generation process: high-confidence fragments returned verbatim, lower-confidence documents synthesized via LLM sampling. This is meaningful behavioral context. It does not explicitly state that the tool is read-only, but the semantics imply it, and no annotation contradiction exists. A score of 4 reflects strong transparency without additional side-effect details.

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 concise sentences with no fluff. It front-loads the core function in the first sentence, then provides usage guidance and alternatives in the following sentences. Every sentence contributes value, making it efficient and well-structured.

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?

No output schema is provided, so the description must convey return behavior. It explains the output type ('concise, ready-to-use answers') and the verbatim vs. summary distinction. It also covers when to use the tool and the role of parameters. It lacks explicit return format details, but for selection and invocation, this is sufficient. A 4 reflects that it is almost complete without specifying exact output structure.

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 100%, so the baseline is 3. The description adds conceptual meaning to the thresholds: directThreshold maps to 'High-confidence results are returned verbatim' and threshold relates to 'lower-confidence ... synthesized into a query-aware summary.' This helps an agent understand the role of each scoring parameter beyond the schema descriptions, meriting a 4.

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: 'Semantic search with automatic summarization.' It distinguishes itself from sibling tools by explicitly referencing search_semantic and search_knowledge, and clarifies its unique behavior of returning verbatim results for high-confidence matches and synthesized summaries otherwise. This makes the purpose unambiguous.

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 provides explicit usage guidance: 'Use this when answering user questions' and directly contrasts with alternatives: 'Prefer search_semantic over this when exploring... Prefer search_knowledge over this when you need full unabridged content.' This clearly indicates when to use this tool and when not to.

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