Vector index data

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

Goes well beyond the coarse annotations (readOnlyHint=false, destructiveHint=true) by classifying each action separately: scan=READ_ONLY, upsert=WRITE, delete=DESTRUCTIVE, sync=EXECUTION+WRITE. It also flags that delete requires confirm and that Delta Sync indexes reject direct writes, which the annotations cannot express.

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?

Front-loaded one-line purpose followed by a tight bulleted action list, a single constraint sentence, and a safety table. Every line carries distinct information with no padding.

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 10-parameter, multi-action tool it covers action semantics, per-action safety, the confirm requirement, and the Delta Sync write restriction; an output schema exists, so return-value detail is unnecessary. An agent has everything needed to choose an action and call it safely.

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%, so the schema already documents every parameter (records, inputs_json, num_results, primary_keys, last_primary_key, confirm, etc.). The description restates the action-to-parameter mapping ('upsert: ... records or inputs_json', 'last_primary_key to continue') but adds little beyond what the per-parameter descriptions already say, so the baseline 3 applies.

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 ('read and write the data') and resource ('inside a Vector Search index'), then enumerates four concrete actions with their effects. This clearly separates it from siblings like query_vs_index and manage_vs_index.

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?

Each action is scoped (scan for paging rows, upsert for Direct Vector Access writes, sync to refresh Delta Sync from source), and it gives an explicit when-not: 'Delta Sync indexes cannot be written directly: modify the source table and sync instead.' It stops short of naming a sibling tool as the alternative for pure queries.

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