Retrieve recently collected values for a host's items, with optional filtering by item name or key fragment to troubleshoot metrics and inspect current state.
Latest collected values of a host's items, optionally filtered by name/key.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | Host name (wildcard allowed) | |
| limit | No | ||
| pattern | No | Item name or key fragment, e.g. 'cpu' or 'vfs.fs' |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered without the description. The description adds nothing beyond that: it does not say whether values may be stale, whether one row is returned per item, or how the limit truncates results. For a read tool whose annotations are complete this is not a contradiction, but it leaves the behavioral burden entirely on structured fields.
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?
A single well-scoped sentence with no wasted words, and the optional-filter nuance is packed in efficiently. It is a fragment rather than a full clause, which slightly weakens front-loading of the action, but nothing is redundant.
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 three-parameter, read-only tool with no output schema, the definition is adequate but thin: an agent still does not know the shape of returned values, how pattern matching behaves (substring versus exact key), or what happens with a wildcard host. The essentials are present, so it is viable but not self-sufficient.
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?
With 67% schema coverage, baseline is a 3. The description's 'filtered by name/key' loosely restates the pattern parameter, which the schema already documents with examples ('cpu', 'vfs.fs'), and it says nothing about host wildcard support matching or about the limit parameter's default of 30 and 200 maximum.
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 description names a specific resource (a host's items) and the exact data returned (latest collected values), which is more precise than the bare tool name. It does not distinguish itself from siblings such as query_metrics_history or get_host_details, so an agent must infer the boundary itself.
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?
There is no statement of when to use this tool versus query_metrics_history (historical data) or get_host_details (inventory-style data). The phrase 'optionally filtered' implies the filter is optional but gives no cue about when to use limit versus pattern, and no prerequisites or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.