add_document

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

With no annotations, the description must carry the behavioral burden; it does disclose the key fact that ingestion is asynchronous and returns a job_id. However, it does not explain job lifecycle, whether the operation is idempotent, or what failure/error behavior the agent should expect.

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?

A single sentence front-loads the essential behavior and return type with no filler; every element earns its place.

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 two-parameter tool with an output schema, the description is mostly sufficient, but it misses the async workflow link: an agent is told it gets a job_id but not advised to poll get_job or that ingestion completion is part of that flow.

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 must compensate. It maps kb to an existing target and pdf_path to a single PDF, but adds little beyond the self-explanatory parameter names and leaves path format/kb identifier details unspecified.

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?

Description names a specific verb ('ingest'), object ('a single PDF'), destination ('existing kb'), and execution mode ('asynchronously'), while noting the job_id return. This clearly separates it from retrieval, removal, search, and KB-lifecycle sibling tools.

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 phrase 'into an existing kb' implies this is only appropriate when the target kb already exists, but there is no explicit when/when-not guidance or link to alternatives such as create_kb (if the kb doesn't exist) or get_job (to track the returned job_id).

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