get_similar_content_by_rag

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

No annotations are provided, so the description carries full burden. It describes the tool as computing similarity and returning matched content, including warnings about citing results. It is transparent about the read-only nature (similarity search) but does not detail any side effects or permissions. Good overall, but lacks depth in behavioral context.

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 well-structured with sections for purpose, usage notes, parameters, and return fields. It is somewhat verbose due to detailed citation formatting instructions, but the core information is front-loaded and clear. Minor redundancy reduces conciseness.

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?

With no output schema, the description thoroughly explains return fields (page_number, file_name, download_url, etc.) and provides usage context. It covers when to use and how to cite results. However, it does not explain technical details like similarity computation method or limits, leaving minor gaps.

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%, but the description compensates by listing the parameter (user_query: str 必填) and its required status. While the schema lacks description, the tool description adds value by clarifying the parameter's role and requirements.

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 explicitly states that the tool computes similarity between user input and document content vectors to find the most similar documents (RAG). It clearly distinguishes from sibling tools (search_report_profile, search_content_detail) which serve different purposes.

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 a clear when-to-use instruction: '当LLM无法从用户输入中提取明确指令时，优先使用此方法' (When LLM cannot extract clear instructions, prefer this method). It also includes citation formatting guidelines. However, it does not explicitly state when not to use or mention alternatives.

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