query_defects

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

With no annotations provided, the description carries the full burden. It discloses the crucial default behavior (all owner params empty → queries 'me'), the accepted input formats (userId/name/account for fuzzy_responser), and the raw JSON return (total/list). While it doesn't mention read-only nature or potential side effects, it's a query tool and the behavior is transparent enough.

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 with a parameter list, a default behavior paragraph, and return format note. It's a bit lengthy but each sentence adds value. The main purpose is front-loaded, and the parameter list is clearly formatted.

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 an 8-parameter tool with all optional parameters, the description provides sufficient context: default behaviors, parameter formats, and return structure. It could mention precedence when multiple owner filters are provided, but the tool can be called correctly based on the given information. The presence of an output schema (not shown) further reduces the need to detail returns.

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 0%, so the description must compensate. It explains every parameter in detail: fuzzy_responser with examples, dev/test responser as userIds, status with default value, priority, summary, and pagination. It goes beyond the schema by providing the type of values (userId vs name) and default behaviors.

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 clearly states the tool '查询缺陷列表' (queries a defect list) with owner-based filtering, which is a specific verb+resource. It also distinguishes itself from the sibling query_my_defects by explaining the default behavior falls back to the same query, making the tool's scope unambiguous.

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?

It explicitly explains when to use this tool versus query_my_defects: the default (no owner params) is equivalent to query_my_defects, and to query others you must pass fuzzy_responser. This gives clear conditional guidance, though it doesn't explicitly say 'use query_my_defects for your own defects' as a shortcut.

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