Build Embeddings

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

Annotations include idempotentHint=true, but description adds key behavioral details: the force option discards existing embeddings, without force the index converges to FTS chunk set, and unchanged chunks are untouched. These go beyond annotations and aid agent understanding.

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 concise, front-loaded with the core purpose, and each sentence adds meaningful detail. No redundancy or wasted 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?

Given a single optional parameter, annotations, and an output schema, the description covers all necessary aspects: what the tool does, when to use it, behavior of both modes, and its relationship to automatic startup. No gaps.

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 coverage is 100%, so the schema already describes the force parameter in detail. The description reinforces the usage scenarios but adds little new semantic meaning beyond paraphrasing the schema. Baseline score is appropriate.

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 rebuilds vector embeddings for semantic and hybrid search, which is a specific verb+resource combination. It distinguishes from siblings like search, read, and reindex by focusing on a maintenance operation.

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 explains that embeddings are built automatically, so the tool is normally not needed, and explicitly describes when to use force=True (after model change) and when not to. It lacks explicit alternatives but provides clear usage context.

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