kb.init

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

With no annotations, the description carries the full burden of behavioral disclosure. It states the tool skips duplicates, returns a summary, and points to a follow-up workflow. However, it doesn't disclose potential side effects like whether existing KB entries are modified, whether the operation is reversible, or any performance/rate limits. The description adds useful context but leaves some behavioral gaps.

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, front-loading the core purpose and then adding important workflow guidance. Each sentence adds value—no wasted words. It is concise yet informative, though the follow-up instruction could be slightly shorter without losing meaning.

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 5 parameters, no output schema, and no annotations, the description covers the main action, skips logic, and post-usage steps. It lacks detail on return format or error handling, but the post-usage workflow compensates for some incompleteness. For a bulk-import tool of moderate complexity, this is reasonably complete.

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 100%, so the baseline is 3. The description adds no additional parameter semantics beyond what the schema provides—it doesn't explain how patterns work, what happens with overwrite=true, or the relationship between project_id and project_root. The schema does the heavy lifting, and the description doesn't augment it.

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 the tool scans a project directory for markdown and text files and bulk-imports them into the knowledge base. It also specifies skipping already-present files and returning a summary. This distinguishes it from sibling tools like kb.add (single add) or kb.search (search), as it's a bulk initialization.

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 post-usage guidance: follow the workflow in .kiro/steering/kb-ingest.md for each added file. It also clarifies the tool skips files already present, implying it should be used for initial import or re-import with overwrite. No alternative tools are named, but the context of bulk import vs. single add is clear from sibling names.

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