discover_tool_input_values
Find exact input values a tool requires from bundled reference data before calling it, preventing guessed identifiers and errors; works offline.
Instructions
Find the exact input values a specific tool requires, from reference data bundled with this server.
Call this BEFORE calling a tool that needs an exact identifier you do not already know. Do not guess the identifier and do not browse the Couchbase documentation website for it -- a guessed value comes back from the target tool as an error with no data. The reference data ships inside this server, so this works offline and while the cluster is unreachable, which is exactly when you are most likely to be looking up a metric name.
Registered today:
tool_name="get_cluster_metrics" -> every Couchbase Server metric name, with its type (counter/gauge/histogram), unit, the server version it first appeared in, and a one-line description. Feed a result's "name" straight into get_cluster_metrics.
tool_name is the only required argument; everything else is optional.
Two ways to call it:
Browse -- pass tool_name alone. Every registered dataset is currently treated as too large to list in full, so this returns "record_count", a small "sample_records" preview, the "chapters" block (the small set of fields you can filter on, with every legal value and a record count each), and a "next_step" pointing you at search instead of a partial list.
Search -- pass tool_name and search_keywords. Returns records ranked by fuzzy relevance, best first. Matching is fuzzy over identifiers and descriptions, so partial words and near-misses still hit.
Every response includes the chapters block, so you never need a separate browse call before narrowing.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| min_score | No | Relevance floor, 0-100. Defaults to 0, meaning nothing is filtered out and you always get the best max_results matches ranked by score, however weak. Check each result's "score" to judge quality -- low scores across the board mean your keywords missed, so change them rather than reading further down the list. Raise this only to suppress weak matches you have already seen. | |
| tool_name | Yes | REQUIRED. The tool you are about to call, e.g. "get_cluster_metrics". An unrecognised value returns the list of registered names, so you do not need to guess twice. | |
| max_results | No | How many records to return. NOT capped by this server -- you are responsible for choosing a value whose response fits your client's output-size limit. If results are too broad, add keywords or a chapter filter rather than raising this. | |
| chapter_filters | No | Optional narrowing, as {chapter_field: value}, e.g. {"category": "Query Service Metrics"}. Only fields listed in the response's "chapters" are accepted (a dataset without chapters accepts none), and multiple filters are combined with AND. Strongly recommended when you know the service: identifiers use short prefixes (kv_, n1ql_, fts_) that keyword search cannot connect to service names, so an unfiltered search for "query service memory" can return Index Service metrics instead. | |
| search_keywords | No | A LIST of words describing what you are looking for, e.g. ["disk", "write", "queue"] or ["index", "resident", "ratio"]. Keep each concept a separate list item. Omit to browse instead of searching. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||