upload_document

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

Goes well beyond the annotations: discloses the 45-second wait window, the three possible status outcomes with their payloads, the accepted file formats, and the ownership requirement on agent_id. That is exactly the operational context an agent needs before invoking a write tool.

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?

Front-loaded with the action, then formats, then wait/status behavior, then args. The Args section slightly duplicates the schema, but each line still adds meaning; no filler sentences.

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?

Covers inputs, ownership preconditions, accepted formats, timing, and outcome states; an output schema exists so return-value shape needn't be restated. Nothing an agent needs to call this correctly is missing.

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 0%, so the description carries the burden and does so: agent_id is constrained to an agent 'you own' (not just any ID), and path is clarified as being on the machine running the server, not the caller's machine — a critical disambiguation absent from the bare 'Path' title.

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?

States a specific verb and resource ('Upload a file ... to a Knowledge Agent') plus the distinctive blocking behavior ('wait for its text'). It is clearly separable from siblings add_text_document (text not file) and get_document_status (status polling).

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?

Gives explicit routing for the async case ('processing' -> check later with get_document_status) and a consent constraint ('Upload only files the user chose'). It doesn't state when not to use it (e.g. prefer add_text_document for raw text), but the context is otherwise clear.

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