[symmetric_cipher] ZUC-128 流密码（中国商密算法）。由于 ZUC 是对称流密码，加解密为同一操作，传入明文即输出密文，反之亦然。key_in_hex 固定 16 字节（32 hex 字符），iv_in_hex 固定 16 字节（32 hex 字符），input_data_in_hex 原始数据长度 1B ~ 16MB。返回字段：output_data_in_hex（输出 Hex）、output_length（字节数）。
| Name | Required | Description | Default |
|---|---|---|---|
| iv_in_hex | No | 初始向量的十六进制字符串，固定 32 个 hex 字符（16 字节） | |
| key_in_hex | No | 密钥的十六进制字符串。长度取决于算法：AES256=64 字符(32B)，AES128/SM4=32 字符(16B) | |
| input_data_in_hex | No | 输入数据的十六进制字符串（加密时为明文，解密时为密文，1B~16MB） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well by disclosing that encryption and decryption are identical operations, key and IV are fixed at 16 bytes, input length is 1B-16MB, and the return fields are output_data_in_hex and output_length. Missing details like output length equivalence or lack of authentication are left unstated, but the provided traits are valuable.
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 compact and information-dense, covering algorithm type, operational symmetry, key/IV sizes, data length bounds, and return fields in a few sentences. No redundant wording or filler; every part earns its place.
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 has no output schema, the description appropriately explains the return fields (output_data_in_hex, output_length) and states key length constraints. It does not provide an example or discuss error cases, but the core details are sufficient for a crypto utility with clear technical constraints.
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?
Although the schema already has 100% description coverage, the tool description clarifies a key ambiguity: the schema's key_in_hex description suggests variable lengths depending on algorithm (AES256=64, AES128/SM4=32), while the tool description fixes it to 16 bytes (32 hex chars) for ZUC-128. It also adds the input data length range and return fields, enhancing schema meaning.
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 explicitly states this is a ZUC-128 stream cipher, a specific Chinese commercial algorithm, and clarifies that encryption and decryption are the same operation. This clearly identifies the tool's function and distinguishes it from generic siblings like stream_cipher by naming the algorithm.
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 for ZUC-128 symmetric stream cipher operations, implying when to use it. However, it does not explicitly discuss exclusions or alternative tools, such as when to prefer the generic stream_cipher or block_cipher, so it falls short of the highest guidance level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct algorithm+operation pair (e.g., rsa_sign vs sm2_sign vs ml_dsa_sign), and descriptions are detailed. However, block_cipher and stream_cipher both perform symmetric encryption, and ecc_key_exchange and hybrid_kex overlap as key exchange, requiring careful reading to distinguish.
Naming is inconsistent across algorithm families: key generation mixes generate_ecc/generate_rsa with ml_dsa_keygen/ml_kem_keygen, and encryption mixes rsa_encryption/sm2_encryption with block_cipher/stream_cipher. Within each family (e.g., rsa_sign/rsa_verify, ml_dsa_sign/ml_dsa_verify), names are predictable, but the overall pattern is not uniform.
32 tools is far above the typical 3-15 range for a well-scoped server. While every tool has a distinct function, the large surface makes the set heavy and harder to navigate, especially with multiple algorithm families and niche utilities.
The toolkit gives comprehensive coverage: key generation, encryption/decryption, signing/verification for RSA, ECC, SM2, ML-DSA, ML-KEM, plus symmetric ciphers, hashing, and key exchange. Full workflows are supported with no dead ends, and even helper tools for debugging are included.