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: it discloses output fields, key sizes, fixed nonce length, the 16-byte auth tag inclusion, and error behavior on tamper detection. However, it omits important crypto-behavioral guidance like nonce uniqueness requirements or explicit statement that ciphertext input for decryption includes the auth tag.

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 into [algorithm], [parameters], [output], and [notes] sections. Every sentence provides essential information—algorithm variants, key lengths, nonce format, output fields, and tamper-detection behavior—with no filler or redundancy.

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?

For a cryptographic tool with no output schema and no annotations, the description is quite complete: it covers input formats, output fields, authentication behavior, and error conditions. It falls short only in edge-case guidance (e.g., nonce uniqueness, exact handling of the auth tag during decryption), but overall it gives an agent enough context to invoke the tool correctly.

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 100%, so the baseline is 3, but the description adds extra meaning beyond the schema: it maps each algorithm to its required key byte length (AES256GCM=32B, ChaCha20Poly1305=32B, SM4GCM=16B), states the nonce is exactly 24 hex characters, constrains input size to 1B~16MB, and clarifies that associated data participates in MAC but is not encrypted.

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 identifies this as a symmetric AEAD streaming encryption/decryption tool ('AEAD 流式加解密'), lists concrete algorithms (AES256GCM, ChaCha20Poly1305, SM4GCM), and distinguishes it from sibling tools like block_cipher and zuc_cipher by specifying the operation types (Encrypt/Decrypt) and algorithm families.

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 implies usage through the '[symmetric_cipher]' label and the word 'AEAD', suggesting it is for authenticated streaming encryption, but it does not explicitly state when to choose this over alternatives such as block_cipher or zuc_cipher, nor does it provide exclusion criteria.

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