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

With no annotations, the description carries the full burden and does well: it discloses read-only behavior, that the tool does not select or predict, and an important behavioral fork — optional BYOK via the X-LLM-Key header for model-polished output versus deterministic review without it. It does not cover cost, latency, or failure behaviour when the snapshot ID is invalid, which keeps it out of 5 territory.

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?

Two tight, front-loaded blocks: purpose plus output, then the operating constraints and the BYOK caveat. The warning glyph makes the optional-header nuance scannable. Slight redundancy in enumerating return fields that the output schema already defines.

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?

An output schema exists, so return values need not be described, yet the description names them anyway as a helpful orientation. Combined with the read-only declaration and the BYOK path, an agent has enough to call this correctly; only edge cases (invalid snapshot, what a 'data gap' means in practice) are unaddressed.

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%, so the schema already documents focus (overall/winners/losers/attribution) and horizon (1/5/20). The description only restates the snapshot_id input and adds no further meaning about how focus or horizon change the report, so the baseline 3 applies.

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 role (复盘分析师), a specific input (scanner 快照 ID), and a concrete output set (收益/基准/超额/命中率、赢家输家、数据缺口、复盘报告), so the agent knows exactly what this tool produces. The scope negation '只读、不选股、不预测、不推荐买卖' separates it from screening/selection siblings like ashare_scanner or ashare_screen, though no sibling is named directly.

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 requirement to supply a scanner snapshot ID implies the workflow ordering (scan first, then review), and '不选股' implies when-not-to-use. But there is no explicit statement of when to pick this over ashare_snapshot, ashare_review, or ashare_scanner, and no exclusions or prerequisites spelled out beyond the ID format.

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