zhiji_ingest_file

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It mentions the specific extraction pipelines (Whisper, Tesseract OCR, document parsing), warns about the time-consuming nature of audio/video transcription on CPU, and details the acoustic emotion analysis, including how isUserVoice affects user profile versus emotion library. No contradictions with annotations.

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 structurally well-organized, starting with the core purpose and sibling distinction, then source options, performance warning, and emotion analysis. It is somewhat lengthy but every sentence adds value. Could be slightly more concise, but the clarity and completeness justify a high score.

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 of the tool (multiple file types, pipelines, performance issues, emotion analysis, parameter interdependencies), the description is comprehensive. It covers what the tool does, how to use it, important caveats, and behavioral traits. However, it lacks explicit mention of return values or confirmation of success, which is a minor gap.

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 schema coverage is 100%, the description adds significant meaning beyond the schema. It explains the rationale behind isUserVoice (acoustic emotion into user profile vs just library), clarifies that filename is used for type detection, and provides context for the three source options with usage recommendations. This enrichment justifies a score above the baseline of 3.

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: ingesting files (audio, images, PDF, etc.) via extraction pipelines (Whisper, OCR, document parsing) into long-term memory. It explicitly distinguishes from the sibling tool zhiji_memory_ingest which only accepts text, using the phrase '只收文本' (only accepts text).

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 explicit when-to-use guidance: for files like audio, images, documents, versus zhiji_memory_ingest for plain text. It explains the three source options (path, url, base64) with appropriate use cases and warnings (e.g., '大文件不建议内联' for base64). It also warns about timeouts for audio/video transcription and cautions about misusing the isUserVoice parameter.

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