bgi_results

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

No annotations exist, so the description carries the full burden, and it does disclose the key traits: it is read-only (只读) and it reveals the data-availability gotcha that one-dragon runs leave no execution records. It omits retention/emptiness behavior when no records exist and any return-format detail, keeping it short of the top score.

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 output content is front-loaded in a single dense clause, followed by a clearly marked 注意 caveat. No sentence is redundant, and the high-value warning sits at the end where it is easy to scan.

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 and no annotations, the description does the necessary work of enumerating the return payload and flagging when records will be absent. It stops short of describing empty-result behavior or format of the failure list, but that is a minor gap for a read-only statistics tool.

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 100%, with date/days/group/material all documented inline, so the baseline is 3. The description only echoes the same concepts (某天/最近几天, 配置组) without adding format or matching semantics (e.g., what 模糊匹配 means for group) beyond the schema.

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 a specific read-only verb and resource ("战果统计（只读）") and then enumerates exactly what it reports: per-route pass/fail, durations, success/failure counts and failure lists, plus farming statistics and task_progress. It implicitly carves itself apart from bgi_run_one_dragon by noting that 一条龙 does not write execution records, though it never names a sibling tool outright.

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 caveat "一条龙不写执行记录，只有配置组任务 / --startGroups / --TaskProgress 会写" tells the agent a precondition for meaningful results, which is genuinely useful routing information. However, it never says when to pick this over bgi_status or bgi_log_search, so the agent must infer the division of labor.

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