add

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

No annotations are provided, so the description must carry the burden. It does disclose a key behavioral trait: URLs are fetched as single pages, not crawled, and paths are absolute and resolve on the server's machine. It also mentions the sync requirement. However, it doesn't disclose side effects (e.g., whether existing files are overwritten) or what happens with OCR or render mode settings, and it doesn't mention error behavior.

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 three sentences: the first states purpose and sync requirement, the second explains path resolution, and the third clarifies URL behavior vs crawl. Every sentence adds critical information with zero filler. It is front-loaded with the primary action.

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 has 5 parameters and an output schema exists, the description covers the most important operational context (path resolution, URL behavior, sync requirement). The gaps are explanation of parameters like 'force' and OCR options, but those are less critical to basic invocation. The presence of an output schema likely explains return values, so the description doesn't need to. A 4 is justified because it handles the trickiest contexts well, though it could mention what the return value indicates.

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 description coverage is 0%, so the description must compensate. The description partially does by implying that 'paths' is the main argument, and it clarifies how URLs are handled (single pages). However, it doesn't explain the semantics of 'force', 'enable_ocr', 'ocr_timeout', or 'render_mode' beyond what the schema minimally hints (e.g., 'render_mode' enum text). A 3 seems right because it adds some meaning for 'paths' and 'render_mode' indirectly but leaves key parameters unexplained.

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 states a specific verb ('add') and resource ('files, directories, or URLs to the knowledge base'), and clarifies the follow-up action ('then sync'). It also distinguishes itself from the sibling tool 'crawl' by noting that URLs are fetched as single pages, which clearly separates its role from crawl's site-wide crawling.

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 gives clear context for when to use this tool (when adding files, directories, or single URLs) and notes an important environment constraint (paths resolve on the lilbee machine, not the caller's when remote). It also provides an explicit exclusion: use 'crawl' for sites. However, it does not detail when to prefer alternative tools like 'import_dataset' or 'sync'.

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