ingest_items

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

With no annotations, the description fully carries the burden. It details every step: image upload to OSS, blockJson formatting, question recording, knowledge mapping, labeling, paper creation, unknown field rejection, duplicate detection, and serial execution for new_models. The return values and batch_id usage are fully explained.

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 fairly concise given the complexity, front-loading the main purpose. It uses bullet points and structured sections. However, it could be slightly more succinct without losing information.

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's complexity, the absence of annotations, and presence of an output schema, the description covers all behavioral, return, and usage aspects. It references AC3, AC4, and PRD-O-005, and connects to sibling tools like 'search_questions' and 'my_recent_uploads'. No gaps remain.

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 input schema itself provides rich descriptions for each parameter, the tool description adds value by explaining the workflow context (e.g., image handling order, serial model proposal) and high-level relationships. The 0% schema coverage in context is inconsistent with the provided schema, but the description compensates adequately.

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 it is a unified ingestion endpoint ('统一入库口') that handles questions, images, knowledge points, labeling, and optional paper creation in one call. It distinguishes from sibling tools like 'ingest_question' (singular) and 'compose_paper' by emphasizing batch and combined functionality.

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 context on when to use (for unified ingestion from seven sources) and references 'get_role_manual' for contract details. It mentions duplicate handling and dual pipeline marking, but does not explicitly exclude alternative tools or state when not to use.

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