policy_market_link

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

With no annotations present, the description carries the full burden and does reasonably well: it discloses the data source (meso_industry_fund_flow), the output fields, and the fallback behavior of the sector parameter ('用于兜底映射'). It does not mention failure modes, empty-result behavior, or the mapping algorithm's limitations, which would make it more transparent.

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?

The description is a single dense paragraph but efficiently packs purpose, behavior, data source, and intended caller into about 75 words with minimal redundancy. It is front-loaded with the core concept ('政策→市场联动桥接'), though a bit of structure (e.g., bullet points for inputs/outputs) could improve scanability.

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?

Given the tool's moderate complexity, the description covers the essential context: what it does, what it returns, where data comes from, and who calls it. The output schema exists to detail the return structure, so not describing it in prose is acceptable. Minor gaps remain around input precedence and edge cases, but an agent has enough to invoke it correctly.

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 baseline is 3. The description largely restates what the schema already explains—url retrieves keywords/sector, sector is fallback, top_n limits results—without adding deeper semantics such as precedence rules when both url and keywords are provided or how the matching algorithm scores relevance.

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?

The description states a specific action (mapping a policy's keywords/sector to industry sectors) and a specific resource (industry sectors with fund flow data from meso_industry_fund_flow), and explicitly lists the returned contents: recent gains, net capital inflow, leading stocks, and representative stocks. It also identifies the intended frontend panel ('市场联动'), which distinguishes it from sibling policy tools like policy_topic_stocks or policy_search.

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 description clearly identifies a concrete usage context: the frontend '市场联动' panel, and explains how to invoke it—provide a policy URL or fall back to keywords/sector. It does not, however, explicitly compare to alternatives such as policy_topic_stocks or state when not to use this tool, so it stops short of full exclusionary guidance.

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