processes

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

With no annotations, the description carries the responsibility and does provide some behavioral detail: it lists read-only, produces a total count, and separates zombies. It does not disclose privileges or server execution, but 'list' is enough of a safey signal to avoid a low score.

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 18-word sentence gets the resource and verb front-loaded unconditionally or memeory, totals, zombies. No filler or repetition; every clause adds behavior.

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?

This is a simple all-optional 3 parameter read tool with no output shape. The description coveys the return value pitfalls (total and zombies), and the schema covers the parameter effects. The only gap is no explicit statement about limit semantics affecting the 'total count', which is a minor negligibility.

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 100%, so the baseline is 3 and the description needs no compensation. The 'by CPU or memory' phrase maps directly to sort_by but does not add nuance beyond param descriptions for limit, server, or sort_by.

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 ('List'), a clear resource (processes), and cements unique scope: top processes sorted by CPU/memory, total count, and zombies separated. This is enough to distinguish it from siblings like docker_list and system_status at a glance, if not by name.

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?

The context That the tool is for inspecting host process is clear, but there is no explicit when-to-use or when-not-to-use, and no mention of alternatives. Rowing to the description, the agent must infer that this is preferable to system_status or docker_list.

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