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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description goes well beyond them: it discloses the cumulative fields returned, the upstream ~1950-bar cap, per-interval retention (8 days at 1m up to 2 years at 60m) that slides daily, the earliest_bar_date_available out-of-range signal, and the Sina keyless source. This is unusually rich behavioral context for a read tool.

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-loaded with the core definition, then the sibling contrast, then return shape and retention limits — a logical order. It is dense and somewhat over-stuffed with near-duplicate example utterances (Chinese and English versions of the same query), which cost space without adding routing value.

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, the description carries the burden and does so: it names the returned bars plus cumulative_volume_shares/cumulative_turnover_cny and earliest_bar_date_available, and documents the cap/retention behavior an agent needs to avoid a doomed call. For a 4-param read tool this is complete.

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 adds real semantics: `up_to` means cumulative sum from the day's open (and 'as of now' if date is today), `symbols` accepts a bare 6-digit code or sh/sz/bj-prefixed form identical to ashares_quote, and `interval` retention shrinks as the interval shrinks. It stops short of adding anything not already echoed in a parameter description, hence not a 5.

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+resource (intraday minute bars for Chinese A-share stocks/ETFs on a given trading day) and the distinctive output (cumulative volume/turnover summed to a requested time). It explicitly contrasts itself with ashares_quote (realtime-only) and ashares_daily_history (end-of-day-only), so an agent can route without opening schemas.

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 explicit when-to-use (a PAST trading day's intraday trajectory), when-not (today/right-now → ashares_quote; daily history → ashares_daily_history), and what to do when the date is out of range (try a coarser interval or fall back to ashares_daily_history). Nothing is left to inference.

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