radar_scan

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

With no annotations the description must carry the burden, and it does: it discloses engine-computed truth/comm with a 0.6 gate, the 0.55–0.65 borderline flag requiring review, and that the calibration bucket is never a content source. These are real behavioral constraints an agent cannot get elsewhere. Minor gaps around performance/cost are not covered.

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?

Front-loads the core pipeline and output promise, then layers scope logic and hard constraints in short, dense lines with no filler sentences. Tightly organized despite the volume of caveats.

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?

No output schema exists, so the description must describe returns, and it does: digest fields (id/标题/truth·comm/来源/日期/new), inline summary depth, and scope_source. Combined with the constraint notes this is nearly complete for a 13-param orchestration tool, with only peripheral params left undocumented.

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 54% across 13 params. The description adds meaning for domain (auto/explicit/broad fallback), briefs, and major_days ('in_window=false 需写明日期'), but leaves top, days, streams, brief_chars, force_refresh, and max_per_source to the schema. Partial compensation, so baseline 3.

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?

States a specific three-step pipeline (采集 + 评分 + 分桶) and its output (可写简报的材料), so the verb+resource is unambiguous. It explicitly distinguishes itself from radar_pack ('要更多正文再用 radar_pack'), but the third sibling radar_check is never mentioned. Strong, though not fully sibling-differentiated.

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?

Gives a concrete default-use rule ('多数情况下一次调用就够写') and names the alternative (radar_pack) plus the condition that selects it (need more body text). Also explains scope auto-detection behavior to guide invocation. No explicit when-not-to-use against radar_check, so not a 5.

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