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

With no annotations, the description carries the full burden and does well: it discloses the return container (extra.fatiao), the fact that each hit is a provision plus parent-regulation metadata rather than full text, and that cost/authorization flow through the caller's OpenAny gateway credentials. It does not mention rate limits, error behavior, or whether rewrite_flag incurs extra cost.

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?

Four sentences, each doing distinct work: capability, filters, return shape, and follow-up routing, with the credential/cost caveat last. Nothing is repeated from the schema and nothing is padding.

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?

There is no output schema, and the description compensates by explaining where results live and what one result contains — the most important missing piece. The remaining gap is that fatiao_filter's allowed values (validity status codes, first-level authority names) are never enumerated, so an agent must guess valid filter inputs.

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, and the description exceeds it by enumerating what fatiao_filter actually filters on — validity status, first-level legal authority, and effective date range — which the bare nested-object schema does not spell out. It adds no guidance on the query-rewrite tradeoff or on the default/max of return_num beyond the schema.

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 (semantic search), resource (securities-industry legal provisions), and granularity ('at the legal provision level'), which is the key differentiator versus a whole-regulation lookup. It does not name or contrast with the many similarly named siblings (e.g. yuandian_post_open_rh_fg_zq_search, yuandian_post_open_law_vector_search), so the sibling differentiation is left implicit.

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 clear routing guidance for the downstream step: results are provision-level, so to get full regulation text 'call the regulation detail API with the regulation ID.' It does not state when to prefer this over the other semantic-search siblings (case search, non-securities law search), so the when-not guidance is absent.

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