architecture

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

Annotations declare readOnlyHint=true and openWorldHint=true. The description adds key behavioral context: 'MCP 负责方法、门禁与结构化证据，不替 Agent 声称绝对最优架构。' This clarifies that the tool does not guarantee optimal architecture, providing important limitations. It also implies structured evidence gathering and gating. No contradictions detected.

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 extremely concise: two sentences that cover purpose, usage modes, composition guidance, and behavioral disclaimer. Every sentence provides unique value. There is no redundancy. It is front-loaded with the core purpose and then adds nuance. Perfect for a tool with many parameters that need schema-level documentation.

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 complexity (19 parameters, nested objects, no output schema), the description does not explain return values or the overall process of ARC-8. However, it sets appropriate expectations by stating the tool provides '方法、门禁与结构化证据'. For a highly complex architecture tool, a 4 is suitable as it covers intent and limitations without over-specifying internal details.

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 68%, meaning many parameters have descriptions. The description adds value by framing the overall purpose and the mode parameter as the entry point. However, many parameters (e.g., 'diff', 'baseline', 'decision') have schema descriptions that already explain them. The description does not deeply elaborate on these, but given moderate coverage, a 4 is justified for reinforcing the context without repeating schema.

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: '独立架构领域能力，使用 ARC-8 完成架构评估、设计、校验和漂移检查。' It specifies the verb ('架构推理与变更'), resource ('架构'), and the four modes (assess, design, validate, drift). This distinguishes it from siblings like 'code_review' or 'code_insight' which focus on code-level aspects, not architecture-level reasoning.

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 says '可直接调用，也可由功能、Bug 或重构流程按需组合', indicating when to call it directly versus compose within workflows. It doesn't explicitly exclude cases or name alternatives, but hints at composition with other flows. A 4 is appropriate because it provides clear context for usage but lacks explicit when-not-to-use or alternative tool mentions.

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