Process resource snapshot

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds meaningful context via 'Sample', implying a one-shot point-in-time read rather than continuous monitoring (differentiating it from the watch tools). It does not disclose sampling duration, rate limits, or whether it blocks for sampleMs, so it adds only partial behavioral value.

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, front-loaded sentence with no filler. Everything stated carries information; nothing needs trimming.

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 4-parameter tool with no output schema and 0% schema coverage, the description is too thin. It fails to explain the device-targeting params, the sampling window behavior, or what a 'snapshot' returns, which an agent needs to call and interpret this correctly.

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 0%, so the description must carry the load, and it only reinforces the single required 'pid' parameter ('for one PID'). The other three parameters (deviceId, deviceName, sampleMs with its 50-5000ms range and 250ms default) are undocumented in both schema and description, leaving the sampling timing and multi-device targeting entirely opaque.

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 gives a specific verb ('Sample') and enumerates the exact resource classes measured (CPU, memory, handles, threads, priority) scoped to 'one PID'. This clearly distinguishes it from process-lifecycle siblings like start_process or kill_process. However, it doesn't differentiate it from closely related siblings such as resource_snapshot or process_resource_watch_read, which likely overlap in intent.

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 when-to-use guidance and no mention of alternatives. With siblings like resource_snapshot, process_resource_watch_start/read/stop, and process_list present, an agent gets no signal for choosing this one-shot sampler over the continuous watch variants. The only implied usage is 'you have a PID and want its stats.'

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