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

Annotations already declare the tool read-only and non-destructive, and the description adds meaningful behavioral context beyond that: only publicly releasable cards are returned, each card is a single fact with no recommendation, and every card returns its source. This materially helps an agent predict what the tool will and will not do.

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 well-structured with labeled Purpose, Guidelines, Limits, and Ex sections, and the purpose is front-loaded. Every sentence contributes either a filter rule, a return characteristic, or an exclusion, with no filler.

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 read-only annotations, full input schema, and existing output schema, the description adds the essential missing context: what kind of cards are searched, how search behaves, what results contain, and what is excluded. An agent has enough information to invoke this tool 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 coverage is 100%, so baseline is 3; the description does add useful semantics by explaining that keyword matches title and fact fields and that type and region combine to narrow results. However, the example uses type='标准解读', which is not among the enum values in the schema, making the parameter guidance partially unreliable.

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 uses the specific verb 'search' and names a unique resource, the public knowledge-card collection, further defining it as atomic sourced facts compiled from statistics, standards, papers, and official announcements. This clearly distinguishes it from sibling query_* tools that target other resource types.

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 gives concrete search guidance: keyword matches title and fact fields, type and region can be combined to narrow results, and each result includes the fact summary and its source. It also states exclusions such as gated/internal cards never being returned, but it does not explicitly name an alternative tool, so the selection guidance is strong but not fully explicit.

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