History (or trends for windows >48h) of up to 5 matching items, downsampled to min/avg/max buckets.
History (or trends for windows >48h) of up to 5 matching items, downsampled to min/avg/max buckets.
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | Host name (exact or wildcard) | |
| item | Yes | Item key or name fragment, e.g. 'system.cpu.load' or 'Memory' | |
| minutes | No | Look-back window in minutes | |
| max_points | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and idempotency, and the description adds genuinely new behavior: a cap of 5 matching items, downsampling to min/avg/max buckets, and a switch to trend data for windows over 48h. It does not say what happens when more than 5 items match (error vs truncation).
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 tight sentence with the key behavioral fact (bucket downsampling) front-loaded and no filler. The parenthetical 'or trends for windows >48h' is slightly compressed but earns its place.
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 no output schema, the description should clarify the return shape (per-item series of buckets?) and the >5-match behavior. It covers the aggregation model but leaves the result structure and overflow handling for the agent to guess.
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 75%, so host, item and minutes are already documented. The description's 'up to 5 matching items' and 'min/avg/max buckets' gestures at the item and max_points parameters but adds no format or semantics for max_points, which is the undocumented one.
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 the resource (metric history) and the transformation applied (downsampled min/avg/max buckets), and notes the trends mode for windows >48h. It is reasonably distinguishable from get_latest_values by the 'history' framing, but it never explicitly names that sibling or states the contrast.
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?
Usage is only implied by the word 'History' and the >48h trends note; there is no explicit 'use this instead of get_latest_values when you need a time window' guidance and no stated prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.