generate_embeddings

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

With no annotations, the description carries the full burden and handles it well: it declares 'Access level: write', describes the success payload shape (processed/skipped/errors counts, duration_seconds), and discloses the specific failure mode RAG_NOT_INSTALLED when the rag extra is missing. It stops short of idempotency/concurrency or auth details, so it is strong but not exhaustive.

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?

Two compact paragraphs: the core behavior and its incremental nature come first, followed by the access/returns/error block. No filler sentences and no repetition of the schema.

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 single-optional-parameter write tool with an output schema already present, the description supplies the essentials an agent needs: write semantics, backfill-only scope, and the RAG_NOT_INSTALLED error path. Only marginal items (permissions, whether re-runs are safe) are absent.

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% for the single scope_id parameter, and the description's 'omit to process every scope' simply restates the schema's own default semantics. Baseline 3 is appropriate since the schema does the work.

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 verb and resource ('Generate or update ChromaDB embeddings') plus a precise scope qualifier ('active rules/lessons whose embedding_id is still NULL'). The phrase 'an incremental backfill, not a full re-embed' cleanly separates it from sibling index_rules_from_markdown / index_lessons_from_markdown, which an agent could otherwise confuse with it.

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?

Gives a clear triggering condition: run only for records with NULL embedding_id, i.e. a backfill of missing embeddings rather than a re-index. It does not name an explicit alternative tool or state when-not to call, which keeps it short of a 5.

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