Build Embeddings

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

The description goes well beyond the annotations by detailing convergence behavior (missing/changed docs embedded, orphans removed, unchanged chunks untouched), inline vs. background execution, soft-deadline semantics, and the immediate return shape with status and job_id. The destructive nature of force=True is disclosed clearly, and nothing contradicts the idempotentHint or destructiveHint annotations.

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 longer than typical, but every sentence carries distinct information: purpose, normal unnecessity, force semantics, convergence behavior, and background execution. It is front-loaded with the core action and progresses logically, though it could arguably be tightened by merging the convergence and background sentences.

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 the output schema, annotations, and sibling context, the description covers all essential operational aspects: when to call, what force does, return behavior, background continuation, and how to obtain the final result. An agent has enough information to invoke the tool correctly and handle both fast and slow builds.

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% and the force parameter already has a detailed schema description. The tool description adds contextual meaning—explaining when force is appropriate and what happens without it—which reinforces the parameter semantics without repeating schema text verbatim.

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 first sentence states an explicit action and resource: 'Rebuild vector embeddings for semantic and hybrid search.' It clearly distinguishes the tool from siblings like embeddings_status (observability) and get_job_result (outcome fetching) by describing the rebuild action and background-job semantics.

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 on startup, so this tool is 'normally not needed,' and gives explicit guidance for when to use force=True (after changing the embedding model). It also references get_job_result and embeddings_status as alternatives for fetching outcomes and observing index state, though it does not provide an explicit when-not-to-use list.

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