get_roll_yield_bar

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the return shape (pandas.DataFrame with a 'ry' column and a date/symbol index), which is useful, but it discloses nothing about data source limits, rate limits, or auth. With annotations carrying the behavioral load, a 3 is appropriate.

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 content is dense with no filler, but the structure is a run-on block that opens with the bare title and then dumps five param lines plus a return line without visual hierarchy. It gets the information across but is not crisply front-loaded around the primary decision (which type_method to use).

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, so the description correctly supplies the return shape (DataFrame, ry column, index by date or symbol). With all five parameters documented and the three modes explained, an agent has enough to call the tool correctly; only the cross-parameter interaction rules are missing.

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%, so the description must carry all parameter meaning, and it does: it documents type_method's three modes, var as a contract code like 'RB'/'AL', and the YYYYMMDD format for date, start_day and end_day. The gap is that it never ties start_day/end_day specifically to the 'date' mode or explains their interaction with type_method, so not a full 5.

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 resource (展期收益率/roll yield) and then breaks the tool into three concrete modes via type_method ('symbol' returns all delivery-month closing prices, 'var' returns a cross-section across all symbols' two main contracts, 'date' returns a per-symbol time series). That is far more specific than a tautology. It does not, however, distinguish itself from the sibling get_roll_yield, so it lands at 4 rather than 5.

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?

By explaining what each type_method value returns, the description implicitly tells the agent which mode to pick for a cross-section vs. a time series. But it never states when to prefer this tool over the sibling get_roll_yield, and it doesn't say which parameters are irrelevant in which mode (e.g. start_day/end_day only matter for 'date'). Usage is implied, not explicit.

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