采购列表

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely useful behavior: dates are millisecond timestamps and 'limit' returns the most recent N records (an ordering semantic not in the schema). It omits default sort order beyond that and any pagination/return-size 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?

A single compact sentence with the core action front-loaded and the filter set and format caveats trailing. No wasted text, though the two clauses could be split for clearer scannability.

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 does not say what fields a purchase record contains or whether results are paginated, and it leaves keyword/category semantics undefined. The readOnly annotation covers safety, but for a 7-parameter list tool some return-shape context is 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 coverage is 57%, so the description must do some compensation. It clarifies the timestamp unit for from/to and the 'most recent N' meaning of limit, which the schema does not fully convey (limit has no description at all). However, keyword and category remain undefined in both places.

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 states a specific verb+resource ('列出采购记录') and enumerates the filter dimensions, so the agent can tell it apart from purchase.get/create/update/delete. It does not explicitly name a sibling alternative, but the list-vs-get distinction is implicit in the filtering language.

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 parenthetical filter list implies when this tool is appropriate (browsing/filtering purchases), but it never states when to prefer purchase.get or how it relates to purchase.list-style siblings like expense.list or project.list. Usage must be inferred from the filter set.

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