Start process resource watch

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

Annotations already declare destructiveHint=true, and the description usefully clarifies the condition under which destruction occurs ('when CPU/memory thresholds are exceeded'), which supports the annotation. It still omits operational traits an agent would want: whether the call blocks or returns immediately, how sampling frequency relates to the run, and where results are later read.

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; the core behavior and its optional effects are stated immediately. It is efficient, though minimal given the tool's complexity.

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 9-parameter, non-read-only tool with no output schema and 0% schema coverage, the description is too thin. It fails to explain defaults, the polling/termination lifecycle, or how the watch is subsequently read or stopped via the sibling tools.

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 carries the full burden. It only loosely implies pid, action, priority, and the CPU/memory thresholds while leaving intervalMs, maxSamples, deviceId, and deviceName entirely unexplained. With 9 undocumented parameters, this is a real gap.

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 and scope ('Continuously sample one PID') plus the two optional consequential actions (lower priority, terminate). It clearly conveys what the tool does. However, it does not differentiate itself from closely related siblings such as resource_governor_configure or the watch_read/stop/list family, so an agent must infer the boundary.

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, no prerequisites, and no naming of alternatives like resource_governor_configure or process_resource_snapshot. The 'start' framing implies it kicks off a monitoring session, but the agent gets no explicit signal for choosing this over the governor or snapshot tools.

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