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

With no annotations, the description carries the full burden and does disclose that execution is asynchronous, that credits are required, and that request_id is an idempotency key frozen across retries. It says nothing about what happens when credits are insufficient, how the caller later retrieves results (get_research_review / get_research_artifact), or failure behavior.

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 front-loaded sentences: purpose first, then the credit prerequisite, then the idempotency contract. No wasted text and every sentence carries information.

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 an async launcher with no output schema, the description conveys the async nature, required credits, and idempotency, which is enough to invoke it correctly. It stops short of explaining the result-retrieval path or credit-exhaustion handling, which an agent would need for a full lifecycle.

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 only 20%, so the description must compensate. It adds real meaning for request_id (generate new per question, reuse on retry) and indirectly maps research_area to the three domains, but research_question, response_language, and the model-freezing rule (covered only in the schema) are unaddressed.

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 (异步梳理, asynchronous review) and resource (公开文献、方法差异与研究缺口), plus the supported areas, so an agent understands what the tool produces. It does not distinguish itself from the sibling start_research_task or prepare_research_task, which sound very similar.

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 prerequisites (needs RigorMed credits) and retry semantics (reuse the same request_id), which imply when to call it. It never states when to choose this over the near-identical start_research_task / prepare_research_task siblings, leaving the selection ambiguous.

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