erinys_forget

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

With no annotations provided, the description fully carries the behavioral burden. It discloses propagation to distilled descendants, leaf-first single-transaction deletion, affected stores (observations/vec/FTS/edges/collisions CASCADE), dry_run non-destructive behavior, and explicit out-of-scope exclusions (Obsidian vault, .bak backups). This is comprehensive and honest.

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 dense yet well-structured, with the core purpose front-loaded in the first sentence. Every subsequent sentence adds meaningful behavioral, transactional, or exclusionary detail, with no irrelevant filler.

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 complex, destructive tool with no annotations, the description is remarkably complete: it covers side-effect propagation, transaction semantics, dry-run mode, and exclusions. The output schema handles return shapes, but the implicit id semantics is a minor completeness 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 schema provides no parameter descriptions, so the description must compensate. It explains dry_run's default and effect, but does not explicitly state that the required 'id' parameter identifies the observation or root node of the closure to forget. Some inference is required for a core parameter.

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 deletes observations and their distilled derivatives from the entire DB substrate and verifies absence via membership test. It explicitly distinguishes itself from erinys_delete by noting it can forget parents with children, making its purpose and differentiation unambiguous.

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 clear context: forgetting propagates to derived descendants, uses a single transaction, and defaults to dry_run. It contrasts with erinys_delete for the specific case of parents with children, but does not explicitly enumerate when to use this tool versus all other siblings, leaving some room for inference.

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