RAG Query

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

Annotations only declare readOnlyHint=true, and the description adds genuinely useful context beyond that: the call consumes the user's AI plan quota, is gated by model permissions, and silently skips knowledge-base retrieval when dataset_key/source_persona_id are absent. The quota-billing disclosure is material for an agent deciding whether to call it. Error and quota-exhaustion behavior is still unstated.

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?

Three compact sentences: purpose and return value first, then cost/permission behavior, then the hard retrieval precondition and dataset-discovery endpoint. Nothing is redundant, though the mandatory-parameter rule is buried after the billing sentence rather than front-loaded.

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?

Wait—reconsider: with 16 parameters, a nested required messages object and zero schema coverage, the omission of parameter documentation is a real completeness gap, so this should not be top marks.

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% across 16 parameters, so the description must carry the load, and it covers only dataset_key, source_persona_id and scene. The required nested messages array, plus model, top_k, top_p, temperature, max_tokens, guidance, guidance_override, tone_hint, tone_hint_override, collection, metadata and system_prompt are all left entirely undefined.

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 (查询) and resource (Ancient Echoes RAG) and states the return contract: an answer plus its sources (返回答案与出处). It is clear what the tool does but never names or differentiates itself from the sibling lingxi.rag_search, which is the closest competing operation.

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?

It gives one concrete usage rule: retrieval only happens when dataset_key or source_persona_id is supplied, and that requirement is waived when scene=coding. It also points to GET /api/v1/rag/datasets for discovery. However, it gives no guidance on when to pick this over lingxi.rag_search, so the most important routing decision is left to inference.

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