get_process_stats

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

With no annotations, the description carries the full disclosure burden. It adds one key behavioral caveat - the shareProcessNamespace requirement - which is essential for setting expectations. It does not state whether the operation is read-only or what happens if the requirement is unmet, leaving a partial picture.

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 sentence front-loads the metric list and appends the prerequisite in parentheses with no filler. Every element 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?

The description covers the core purpose and the critical prerequisite, which is enough for an agent to decide whether the tool is viable. There is no output schema, so the return format is not described, and potential failure modes are not mentioned, leaving moderate gaps.

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?

All three parameters (pod, service, namespace) have 100% schema description coverage, so the schema already documents their meaning. The description adds no parameter-specific detail, matching the baseline of 3.

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 specifies exactly which metrics are retrieved (RSS, threads, file descriptors vs limit, state, uptime) and scopes them per process, making the tool's purpose unambiguous. The '[probe]' marker signals a diagnostic read. It does not explicitly contrast with sibling tools, though the metric list separates it from JVM- or network-focused siblings.

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 description implies use when OS-level process statistics are needed and adds a concrete prerequisite (shareProcessNamespace) for seeing the app, which is useful contextual guidance. It does not state when to prefer an alternative tool or when not to use this one, so the guidance is implied rather than explicit.

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