kb_ingest

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

Discloses that this is a promotion into the shared KB, the guardian-consent seam requiring a verified kb_promotion grant for non-owner subject data, that subject_id is opaque and never written, and that committed promotions are logged to the subject's disclosure chain. This adds substantial behavioral context beyond the sparse annotations, though the effect of the supersede parameter is not explained.

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 organized into tight thematic chunks: purpose, prerequisite, slice selection, exclusions, and subject_id handling. Every sentence adds domain value, though the subject_id paragraph is dense and could be broken out more cleanly.

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?

Strong coverage of source requirements, slice options, forbidden content, and consent/grant behavior for a mutation tool with no output schema. But it omits semantics for tier, supersede, and sensitivity, and does not describe return/error behavior, leaving meaningful gaps for a 7-parameter tool.

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?

With 0% schema description coverage, the description compensates for slice (listing voice_only | work_context | full and the exposure.json default) and subject_id (guardian-consent semantics). However, tier, supersede, and sensitivity are left unexplained, and agent_id only appears inside a file path, leaving several parameters underspecified.

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 action—promote a ratified agent_seed slice into Postgres KB—and narrows the resource to agent_seed slices with explicit exclusions (persona.cast, context.personal_note). This clearly differentiates it from sibling ingestion/promotion tools like knowledge_ingest and kb_promote.

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?

Provides explicit prerequisites (ratified + trusted seed at $WILLOW_HOME/seeds/{agent_id}.json), valid slice values, and a clear rule about what it never promotes. It does not explicitly name an alternative tool for excluded content, so the guidance is clear but not strongly comparative.

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