Vector Search endpoints

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

Goes well beyond the annotations by classifying per-action safety (list/get = READ_ONLY, create/update = WRITE, delete = DESTRUCTIVE), disclosing that provisioning is long-running and returns 'pending', that delete requires confirm, and that update's custom_tags REPLACES all tags. This is exactly the extra context annotations alone can't convey.

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?

Bulleted by action with a compact spec summary, then a one-line safety classification. Every line carries information and the scan order (actions first, safety last) is sensible.

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?

With an output schema present, return values need not be described, and the description covers the remaining gaps an agent needs: long-running provisioning, confirm gating, dry_run semantics, and per-action risk. Nothing material is missing for correct invocation.

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 baseline is 3, but the description adds real meaning: which spec fields apply to create vs update, that custom_tags overwrites existing tags, the confirm workflow tied to 'confirmation_required', and the wait_seconds default behavior. Only the pagination params (page_size/page_token) are left to the schema.

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?

Opens with a specific verb+resource and parenthetically explains what an endpoint is ('the compute that hosts vector indexes'). The action enumeration (list/get/create/update/delete) makes it immediately distinguishable from siblings like manage_vs_index or query_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 annotated with required inputs and behavior, and it explains when to set wait_seconds (only if you want to block for ONLINE) versus taking the immediate 'pending' return. It does not explicitly route the agent when to pick this over manage_vs_index/manage_vs_data, so it stops short of a 5.

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