backfill_query_embeddings

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

No annotations are provided, so the description bears full responsibility. It discloses batch processing and the optional index building, but omits details like error handling, performance impact, or whether the operation is reversible.

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 concise sentences, each providing unique information: purpose, batching, and the build_index option. No unnecessary words.

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 an output schema existing, the description does not mention what the tool returns (e.g., count of rows affected, success status). This is a significant gap. Also, batching mechanics (e.g., order, progress feedback) are vague.

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 0%, yet the description only explains build_index. batch_size, limit, and dry_run are not elaborated, leaving the agent to infer their purpose from names alone. This is insufficient for a tool with 4 parameters.

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?

Description clearly states the specific action: backfilling the query_embedding column in retrieval_telemetry for rows predating Phase 4a. This distinguishes it from sibling tools like kb_backfill_embeddings.

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?

Description mentions batching and the build_index option for index creation. While not explicitly stating when not to use, the context (retroactive backfill) is clear. No alternatives are named, but the sibling context provides differentiation.

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