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

Annotations already fully cover the safety profile (readOnly, idempotent, destructive=false, openWorld=false), so the bar is lower; the description nonetheless adds real behavioral context the annotations do not convey: excluded cards are filtered at export and never returned, and each card is a single fact with no recommendation. It does not cover pagination/return-shape behavior, but the output schema handles that.

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 Purpose/Guidelines/Limits/Ex/Scope labels and every section carries information; no filler sentences. It runs slightly long, and the starred Scope paragraph does a lot of work that could be tightened, but nothing is wasted.

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 a full output schema and complete annotations, the description only needs to add selection and content semantics, which it does (filtering rules, card granularity, when to prefer query_domain_benchmarks). The only shortfall is the enum-inconsistent example value, which leaves a small ambiguity about accepted type inputs.

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% (including offset/next_cursor and response_format), so baseline is 3. The description adds useful matching semantics (keyword scans title and fact fields; combine type and region) and worked examples, but the example query_cards(type='标准解读') uses a value that is not in the type enum (statistic/standard/paper/announcement/industry_association), which risks misleading the agent.

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 ('search the public knowledge-card collection') and immediately qualifies what a card is (atomic sourced facts compiled from statistics, standards, papers, announcements). The Scope note explicitly differentiates it from the sibling query_domain_benchmarks, so an agent can choose between them without opening either schema.

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 concrete when-to-use rules (keyword matches title/fact fields; combine type and region to narrow), explicit exclusions (legacy rCB-centric layer, small curated set), and names the preferred alternative for multi-domain facts with the reason (current, larger benchmark layer). 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.