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: it discloses the institutional-tier restriction, warns that non-quarter-end dates return empty (not a fault), explains available_dates and the is_fallback flag when the requested date was not honored, and notes total_net can be negative. These are exactly the traits an agent cannot infer from structured fields.

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 resource and return-field inventory, then usage, then the critical constraint, then disambiguation warnings. Dense but every block earns its place; the repeated ⚠️ markers and bolded caveats add slight visual noise but aid scanning rather than pad length.

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, yet the description still summarizes the row fields (plate_code/plate_name/raw) and top-level fields (date, total_net, total_hold, available_dates), and covers the access tier, the date constraint, and sibling confusion risks. For a two-parameter, no-annotation tool this leaves nothing an agent needs 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 schema already documents date and limit, including the quarter-end format. The description adds operational meaning to date beyond the schema: blank means latest quarter end, non-quarter-end yields empty results, and available_dates enumerates valid periods. The limit parameter is not discussed, keeping it just short of 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: quarterly northbound (foreign) capital holdings broken down by sector. It explicitly disambiguates from siblings by declaring 'this is the sector dimension, not individual stock holdings' and 'not the same as ashare_fund_south (Hong Kong Stock Connect southbound)'.

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?

Names the user questions that should route here ('foreign capital buying which sectors / how much northbound holdings / northbound flow') and explicitly routes southbound questions to ashare_fund_south. It also gives the precondition that a quarter-end date must be supplied and states the auto-fallback when omitted.

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