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

With no annotations, the description carries the full burden and does so: hard caps (Pro 500 / unlimited 1000), measured latency at 200/500/1000/3000 codes, per-code status instead of silent drops, billing charged only on actually returned codes, paid-tier requirement (¥99 Pro+), and the critical constraint that only daily bars exist so week/month/m30 silently yield daily values.

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?

Content is front-loaded with a starred one-line summary and then segmented ⚠️ blocks for relationship, limits, usage, period constraint, return shape, and billing. Dense and emoji-heavy, and the per-code-count latency figures are somewhat redundant with the stated caps, but nearly every sentence carries a distinct operational caveat.

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 a batch tool with an output schema present, this explains the return shape anyway (data array of {code, ok, data|error}, 55 columns mirroring /v1/technical, plus requested/returned/failed counts), covers failure semantics, cost, and access tier. Nothing an agent needs to call it correctly or interpret partial failures 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 100%, so the baseline is 3, but the description still adds real meaning: comma-separated codes with bare 6-digit support, mixed A-share (incl. Beijing exchange)/HK/US in one call, index codes like sh000001, and non-trading-day auto fallback for `date` which applies to all codes at once. Minor friction: '专业版 500 只 / 不限量 1000 只' is awkwardly phrased and slightly out of step with the schema's '机构版 ≤1000'.

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 verb and resource — batch retrieval of 55 named technical indicators (MA/EMA/MACD/KDJ/RSI/BOLL/...) with per-code success flags. It explicitly distinguishes itself from the sibling ashare_technical by explaining that the single-code endpoint returns one wide table with no per-code status and silently drops invalid codes.

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 the triggering user questions verbatim ('这批股票的技术面怎么样/哪些金叉了/哪些超买了'), states the rule 'multi-code → use this tool,' and explicitly permits single-code use. It also contrasts the alternative path (looping 500 calls = 500 requests, ~8 min, hits rate-limit backoff), so the agent has both when-to-use and when-not.

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