Metis — KG Index Notes

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

With no annotations, the description carries the burden and does substantial work: it discloses what gets written (bidirectional note_links edges from YAML `related:` and `[[wikilinks]]`), where configuration comes from (METIS_OBSIDIAN_VAULT env var or `obsidian_vault:` in user-config.yaml), and that re-runs use REPLACE semantics. It stops short of saying whether notes removed from disk lose their edges, which would be the next useful disclosure.

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?

Three compact sentences, front-loaded with what is indexed, then the parsing behavior, then the configuration instructions. Nothing is padded, though the trailing comma/clause formatting is slightly disjointed rather than a single tight paragraph.

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?

With an output schema present, return values need not be described, and the description covers scope, side effects, configuration prerequisites, and idempotency — enough for an agent to call it correctly. The only gap is lifecycle behavior for notes that disappear from disk after a prior index run.

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?

There are zero input parameters, so the baseline is 4. The description usefully explains the de facto configuration inputs (env var and user-config.yaml key) that a caller must set before invoking, which is real value beyond the empty schema.

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?

Specific verb ("Index") plus specific resource (".md notes") and destination (the knowledge graph), with the exact scopes named (knowledge/library/ and an optional Obsidian vault). It is clearly distinct from kg_index_memory by resource type, though it never names that sibling explicitly to rule it out.

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?

Usage is implied by the operation itself and by the note that re-running is safe, but there is no explicit statement of when an agent should run this versus kg_index_memory, index_pending_layers, or scan_library, and no stated preconditions beyond vault configuration.

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