capacity_forecast

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully adds the return fields (predicted date, growth rate, R-squared) and the regression method, but says nothing about data prerequisites, error behavior, or how sparse history affects the forecast.

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 tight sentences: method first, outputs second, use case last. No filler and the core behavior is front-loaded.

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 and annotations cover safety, so the description does not need to explain return values. It is nearly complete, though it omits any note on data prerequisites or what happens with insufficient historical samples for a regression.

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%, so hostid, item_key, period, threshold, server, and raw_json are all already documented, including the detailed raw_json policy warning. The description adds only the conceptual link between threshold/period and the forecast, so the baseline 3 is appropriate.

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 (forecast), resource (metric), and method (linear regression on historical trend data), and even names the outputs. It is clearly distinct from sibling read tools like trend_get, but it does not explicitly position itself against the closest neighbors (anomaly_detect, item_threshold_search).

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?

'Useful for capacity planning (disk, CPU, memory)' implies the intended context but gives no when-not conditions and never names an alternative tool for cases where forecasting is inappropriate (e.g. when the agent just needs raw history).

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