list_bucketsList the buckets of one storage connection that this access grant can see. list_connections already includes the buckets. Use this tool to refresh the buckets of one connection.
| Name | Required | Description | Default |
|---|---|---|---|
| connectionId | Yes | Connection ID from list_connections |
| Name | Required | Description | Default |
|---|---|---|---|
| stale | Yes | ||
| buckets | Yes | ||
| refreshedAt | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / refreshedAtAdded value: +{
+ "type": "string"
+}Output schema / properties / staleAdded value: +{
+ "type": "boolean"
+}Output schema / requiredPrevious value: -[
- "buckets"
-]New value: +[
+ "buckets",
+ "refreshedAt",
+ "stale"
+]Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "https://json-schema.org/draft/2020-12/schema",
+ "additionalProperties": false,
+ "properties": {
+ "buckets": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "buckets"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real context: the result is permission-scoped to the access grant and overlaps with what list_connections returns, so it is a refresh path rather than a new data source. It does not mention pagination or behavior on an invalid/stale connectionId, so it falls short of the richest disclosure.
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 sentences, front-loaded with the scope and the resource, then the relationship to list_connections, then the use case. No sentence is redundant and nothing is buried.
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?
An output schema exists, the single parameter is fully documented, and annotations carry the safety profile, so the description only needs scope and routing guidance — both of which it provides. Nothing an agent needs in order to call this correctly is missing.
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% and the single parameter already documents itself as 'Connection ID from list_connections'. The description only restates 'one storage connection' and adds no format, sourcing, or error semantics beyond the schema, 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 and resource ('List the buckets') scoped to 'one storage connection' and further constrained to what 'this access grant can see'. It also implicitly distinguishes itself from list_connections, so an agent can tell the two apart without opening either schema.
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?
Names the alternative (list_connections) and states explicitly that it already includes buckets, then gives the single condition that selects this tool: 'Use this tool to refresh the buckets of one connection.' That is an explicit when-to-use plus an implicit when-not.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.