derivation_differentiate

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

No annotations are provided, so the description bears full responsibility for disclosing side effects. It mentions '帶人類知識記錄' (with human knowledge records), indicating it captures notes/assumptions/limitations, but it does not disclose whether this mutates session state, replaces the current expression, or has side effects. No error behavior, prerequisites, or output format details are given.

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 concise and front-loaded with the main purpose, followed by a compact parameter list. It avoids unnecessary fluff, but the parameter explanations are terse and the return section is just '微分結果' (differentiation result). Overall, it is well-structured for its length.

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 operates on a 'current expression' and interacts with many derivation session tools, the description lacks essential context: how the current expression is set, whether this updates the session, prerequisites (e.g., session started), and the detailed return structure. The output schema is not shown, so the description alone is insufficient for safe standalone use.

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 explain parameters. It lists variable, order, description, notes, assumptions, and limitations with brief explanations (e.g., '微分變數' for variable, '階數（預設 1）' for order). However, it omits session_id entirely, and the explanations are minimal, lacking format or usage details for assumptions/limitations arrays.

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: '對當前表達式微分' (differentiate the current expression). It also mentions the human knowledge recording aspect, which distinguishes it from pure computation tools. However, it does not explicitly contrast with sibling tools like derivation_integrate, though the verb 'differentiate' is specific.

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 no explicit guidance on when to use this tool versus alternatives. It mentions 'current expression' implying a session context, but does not state prerequisites (e.g., needing an active derivation session) or when to prefer differentiation over other operations. No exclusion or alternative tools are referenced.

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