get_shfe_rank_table

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral context: the data source URLs, the limitation that only per-product rankings are available (no product totals), the historical start date, and the update schedule. It also details the return fields. This goes beyond the annotations and helps the agent understand what to expect, though it does not cover potential pagination or error behaviors.

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: title, source URLs, note, data availability/update time, parameter documentation, and a detailed return field table. Each section serves a purpose and the critical note about no total ranking is front-loaded among the notes. While it is long, the field table is informative and the structure is logical. It is not overly repetitive and earns its length.

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 a 2-parameter tool with no output schema, the description is quite complete: it gives source URLs, data history, update timing, a key limitation, parameter docs, and a field-by-field return description. The primary gap is the lack of the top-level structure of the returned dict (e.g., how the fields are organized into keys), and it does not clarify that vars_list must be restricted to SHFE products despite the schema default containing non-SHFE codes. Still, the level of detail is high and covers most context an agent would need.

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?

With 0% schema description coverage, the description carries the full burden for parameters. It explains 'date' as the trading day (str) and 'vars_list' as contract varieties like RB and AL, noting that an empty list returns all commodities. This adds meaningful semantics beyond the bare schema. The format of date (YYYYMMDD) is implied by the return field description. The explanation is useful but could be more explicit about the valid codes for SHFE specifically, especially given the schema's default list includes non-SHFE contracts.

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 opens with the Chinese title '上海期货交易所会员成交及持仓排名表' which clearly identifies the tool as retrieving Shanghai Futures Exchange member volume and position rankings. The note that the exchange only publishes within-product rankings and not total product rankings helps distinguish this tool from siblings like get_rank_sum or other exchange-specific rank tables. The purpose is clear, though it relies on the tool name for the verb rather than having an explicit action word in the description.

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 contextual guidance: it is specific to SHFE, data starts from 20020107, and updates around 16:30 each trading day. The note about no overall product rankings is an exclusion, but there is no explicit mention of when to use this tool versus alternatives such as get_cffex_rank_table or get_dce_rank_table. Usage is implied by the SHFE name and the note, but the description does not name alternatives or state clear when-to-use/when-not-to-use scenarios.

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