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

With no annotations, the description carries the full burden and does disclose key traits: the call is anonymous-callable ([匿名可调用]), it is a read-only lookup, and it produces a prompt that must act as an external MCP agent's system prompt governing downstream quotation wording and templates. It does not describe what happens on an invalid URI or what an unlisted URI returns, which is the remaining gap.

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 capability and URI list come first, then the scenario workflow, so it is well front-loaded with no filler sentences. The second half is a single long run-on clause that is slightly denser than needed, but every sentence carries operational 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?

For a one-parameter read tool with no output schema and no annotations, the description supplies the URI catalog, the anonymous-access note, the sibling routing rule, and the mandatory ordering with plan_quotation - enough to call it correctly. Missing only error behavior for bad URIs and any sense of return shape.

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 0%, so the description must compensate, and it does by enumerating the valid URI values with short glosses (状态码, 联系人, 健康画像, 企业团检方案顾问引导词). It does not state whether uri is required, what the format/prefix convention is beyond the examples, or whether unlisted URIs exist.

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 verb and resource ("按需查询领域知识" - query domain knowledge on demand) and immediately enumerates the concrete knowledge artifacts available (enums, objects/contact, objects/contact-profile, objects/checkup-proposal). It also distinguishes itself from the sibling help() tool by routing 'action parameter' lookups there.

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?

Explicit routing is given for two cases: use help() for action parameters, and in the group checkup quotation scenario load knowledge_get({uri:"objects/checkup-proposal"}) FIRST, then call plan_quotation. The ordering constraint and the alternative tool are both named, leaving nothing to inference.

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