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

Annotations already cover the safe read-only, idempotent, closed-world profile, but the description adds two things they cannot: the return is counts only with no agency IDs, and each call is billed once. The billing disclosure is materially useful for an agent deciding whether to call repeatedly. It stops short of stating behavior for an invalid or delisted ts_code.

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?

Four short sentences that are front-loaded with the purpose, then the returned metrics, then the key exclusion, then the billing note. Nothing is redundant and no sentence could be dropped without losing information.

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 correctly takes on the job of enumerating what comes back (rolling 7/30-day dedup counts, cumulative new coverage, 30-day high-score share), which is enough to judge fitness. Minor gap: it never defines what counts as '机构/大V' or how min_score's scale works, so an agent cannot sanity-check the 30-day high-score ratio.

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 every parameter is already documented, including the ts_code/stock_name either-or and min_score's role in high_score_ratio_30d. The description restates the 7/30-day windows and the high-score ratio but adds no format, unit, or cross-parameter guidance beyond the schema. 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?

It names a specific resource and output shape: daily time series of institutional/big-V coverage counts for one stock, and it contrasts with the family of tools that return ID lists ("只给计数，不返回机构 ID 列表"). This distinguishes it from siblings such as get_agency_history or get_agency_ranking, although it never names an alternative tool explicitly.

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?

Usage is only implied: an agent can infer this is the statistical-summary option versus ID-level agency tools. There is no explicit when-to-use/when-not-to-use statement and no note that ts_code or stock_name must be supplied, even though that constraint decides whether the call succeeds.

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