derivation_start

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses that sessions are automatically persisted to prevent interruption ('會話會自動持久化，防止中斷') and that the tool returns session information. However, it does not disclose potential side effects, permission requirements, or what happens if the session already exists. The provided behavior is somewhat minimal but not misleading.

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 Args, Returns, and Example sections, making it easy to scan. It is concise and each section serves a purpose. The bilingual mix (Chinese description, English example) is slightly awkward but does not detract from clarity. It could potentially be shortened, but overall it is appropriately sized.

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 that there are no annotations but an output schema exists, the description sufficiently covers the tool's purpose, parameters, return value (via example), and a key behavioral trait (persistence). It is complete for a simple creation tool, though it lacks explicit error conditions or prerequisites. The example return object partially compensates for the unspecified output schema.

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 0%, so the description must compensate. It does so by explaining each parameter in Chinese: 'name: 推導名稱' (derivation name), 'description: 推導描述' (derivation description), 'author: 作者' (author), and provides a concrete example with expected output. This adds meaningful semantic context beyond the bare schema, though it could be more detailed about data formats or constraints.

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 '開始新的推導會話' (start a new derivation session) and identifies itself as '這是一切推導的起點' (the starting point for all derivations). This specific verb+resource combination, along with the explicit '起點' framing, distinguishes it from sibling tools like derivation_resume or derivation_complete.

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 clear context that this tool is the entry point for all derivations ('這是所有推導的起點'), implying it should be used before any other derivation tools. It also notes that sessions auto-persist to prevent interruption, which is a relevant consideration. However, it does not explicitly mention alternatives or when not to use it (e.g., use derivation_resume for existing sessions).

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