Upload Asset

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

Annotations already establish this as a non-read, non-idempotent write operation. The description adds the base64 transport requirement and the RAG parsing side effect, which are useful beyond annotations. However, it does not disclose whether parsing is asynchronous (lyzr_get_asset_parse_status suggests it is), whether upload credentials are required, or what the response contains.

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?

Two sentences, roughly 22 words, with the primary purpose front-loaded and the critical base64-encoding requirement stated in the second sentence. Every word earns its place; there is no repetition of schema details or annotation 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?

This is a complex tool (12 params, 11 optional parsing controls) with no output schema, yet the description explains neither the return value (e.g., asset IDs/parse status) nor how to track an async parse. It also offers no guidance on navigating the many parsing options (page ranges, VLM providers, chunking strategies) or follow-up steps like polling lyzr_get_asset_parse_status. The schema's per-parameter descriptions help, but the operational flow is left for the agent to infer.

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?

With 100% schema description coverage, the baseline is 3; the schema already documents all 12 parameters, including the parse_config JSON shape. The description adds marginal value by framing the parse/chunk parameters as optional and RAG-oriented, but terse string params (vlm_model, parsing_mode, parser_provider, chunking_strategy) remain underspecified with no enum choices or examples, and the description does not compensate.

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 uses a specific verb ('Upload') tied to a clear resource ('files as assets') and adds distinctive scope with 'optionally parsing/chunking them for RAG.' This clearly distinguishes it from sibling parse-only tools (lyzr_parse_pdf, lyzr_parse_docx) and KB training tools (lyzr_kb_train_pdf), which handle parsing or training but not asset creation.

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 RAG parsing mention implies when to use it (ingesting files for RAG workflows), but there are no explicit when-to-use/when-not-to-use instructions or named alternatives among the many siblings. An agent gets no direct guidance on choosing between this and lyzr_kb_train_pdf, lyzr_parse_pdf, or lyzr_kb_train_documents for seemingly similar workflows.

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