agent_catalog

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

With no annotations provided, the description fully discloses behavioral traits: it is read-only ('[L:READ]', '风险：READ'), public authentication ('鉴权：PUBLIC — 纯索引，不查任何 API'), takes no parameters, returns a small (~5KB) structured index of 12 domains. There are no contradictions between description and any implicit annotations.

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 clear tags ([L:READ], CAT, etc.), a function overview, usage scenarios, keywords, parameter note, authentication, risk, and return size. Despite being in Chinese, each section is concise and adds unique value. The information is front-loaded with the most critical details (read-only, public, entry-point tool). No extraneous content.

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 simplicity (no parameters, no output schema), the description provides all necessary context: it explains the tool's role in the navigation workflow, the structure of the returned map (12 domains grouped by intent), the small response size, and the relationship to agent_catalog_detail. An agent can fully understand when to use this tool and what to expect without additional information.

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?

The tool has no parameters, and the input schema is empty (100% coverage). The description explicitly states '参数：无', confirming no input is required. While the schema alone already conveys this, the description adds clarity by reinforcing the absence of parameters and explaining that no user input is needed. Since the schema coverage is complete, a baseline of 3 applies, but the explicit confirmation and additional context (e.g., '纯索引') justify a score of 4.

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 clearly states the tool's purpose as a global tool navigation ('全局工具导航') and designates it as the first tool to call upon initial connection. It specifies that it returns a tool map grouped by user intent, distinguishing it from sibling tools like agent_catalog_detail, which handles domain-specific details. The verb-resource pairing is explicit and unambiguous.

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 provides explicit usage scenarios: 'Agent 首次连接 hvip MCP 后第一个应调用的工具' (first tool on first connection) and '不确定该用什么工具、想了解 hvip 能做什么' (when unsure what tool to use or wanting to understand capabilities). It also outlines a workflow: start here, then use agent_catalog_detail for domain details, then directly call target tools. This gives clear when-to-use and when-not-to-use guidance.

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