kg_init

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

No annotations are provided, so the description carries the full burden. It mentions overwriting but does not disclose whether creation is destructive to existing files (beyond overwrite), side effects, or required permissions. Lacks details on concurrency or failure modes.

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 brief with two main sentences and a third about rendering. It is front-loaded with the primary action. The third sentence is mildly extraneous but does not detract.

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?

Despite having an output schema (not shown), the description does not mention what the tool returns or what happens after creation (e.g., confirmation, path). For a tool that creates a file, this is a notable gap.

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?

The description adds no extra meaning beyond the input schema, which already covers all four parameters with descriptions. Schema coverage is 100%, so baseline 3 is appropriate.

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 creates a new knowledge graph file (markdown) with a specific verb and resource. It distinguishes from siblings like kg_add_service (adds a service) and kg_lint (lints), which are different operations.

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 implies that the knowledge graph is a persistent source of truth and that diagrams are rendered from it, but it does not explicitly state when to use this tool vs alternatives (e.g., kg_import for importing an existing graph) or when not to use overwrite.

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