embed_index

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

No annotations provided, so description carries full burden. It discloses batch processing, need for repeated calls, and that it only processes messages without vector. However, it does not mention side effects, idempotency, or error handling, but the key behaviors are covered.

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 short, efficient sentences in Russian. Front-loaded with purpose, then usage, then alternative. No fluff, every sentence adds value.

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?

Covers main purpose and usage pattern, but lacks return value structure (only mentions has_more flag, not how to access it) and prerequisites. Without output schema, description should provide more detail on what the tool returns.

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?

Input schema has one optional parameter 'batch' with default 300, but schema description coverage is 0%. The description says 'one batch' implying batch size, but does not explicitly link the parameter name to its meaning. An agent can infer, but it's not explicit.

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 indexes one batch of messages without vector (generates embeddings). It distinguishes from siblings like search_messages or semantic_search by focusing on batch indexing rather than retrieval or synchronization.

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?

Explicit guidance: 'Call repeatedly while has_more=true' and mentions alternative scripts/embed_backfill.py for full reindexing. This helps an agent decide when to use this tool versus alternatives.

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