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

No annotations are supplied, so the description carries the full burden, and it does add non-obvious operational context: the request body must not be empty, credentials come from the caller's OpenAny gateway, and 'charges and authorization are determined by the gateway' warns of possible billing/entitlement gating. It omits failure behavior (unknown id or fgmc) and does not clarify what 'related information' contains.

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?

Front-loaded with the identification and locator rules before the return-shape sentence and the gateway note; nearly every clause carries information. The closing gateway/billing sentences are slightly verbose and could be compressed, but 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?

With no output schema, the description compensates by enumerating the returned fields (provision text, number, parent regulation id/name, validity status, publication and effective dates). Combined with locator precedence and point-in-time selection, an agent has enough to call it correctly; only error/empty-result behavior is unspecified.

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 already 100%, so the baseline is 3, but the description adds semantics the schema lacks: the precedence of id over fgmc/ftnum, the requirement pairing of fgmc with ftnum, and that refer_date selects a historically effective version rather than a plain filter. These are decision-relevant rules beyond the field descriptions.

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 and resource ('Retrieves details of a single legal provision') and the description makes clear it is a single-record lookup rather than a list/search. It does not name the sibling it replaces, so an agent must infer that yuandian_post_open_rh_ft_search is the discovery step that precedes this detail call.

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 concrete routing rules inside the tool: 'id takes precedence when locating the provision; alternatively, use fgmc with ftnum', plus 'refer_date can be supplied to locate the version applicable on a specified date'. That is genuine when/how guidance, though it says nothing about when to prefer this over the sibling search endpoints or what to do when no matching provision exists.

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