proc

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

With no annotations, the description carries the full burden. It does add real value: the confirm=true guardrail for killing by name, the destructive kill semantics, and the cross-platform implementation (ps on Unix vs PowerShell/tasklist on Windows). It omits permissions required, reversibility, and output characteristics for a tool that can terminate processes, so it is not fully transparent.

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?

It is a single dense sentence that is front-loaded with the resource and organized as labeled per-action clauses, so nothing is wasted. The heavy parenthetical nesting and run-on length keep it from being maximally scannable, but it is efficient.

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, multi-action, destructive-capable tool with no annotations and no output schema, the description covers the action surface and cross-platform behavior but leaves gaps: no return/output shape is described (only a max_bytes hint exists in schema) and no safety or permission caveats beyond confirm=true. Adequate but not complete for the complexity.

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 every parameter is already documented in the schema and the baseline is 3. The description largely restates schema content (filter by name, sort by cpu/memory, kill by pid) rather than adding syntax or edge-case meaning beyond what the schema provides.

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 names the resource (processes on this machine) and enumerates four distinct operations (list/tree/info/kill) with what each does, so an agent immediately knows this is a process-inspection/control tool rather than general shell execution. It does not explicitly name any sibling to rule out (e.g., shell_exec), so it stops short of full sibling differentiation.

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?

Usage is implied through the action-by-action breakdown (filter by name, sort by cpu/memory, kill by pid or name), which gives an agent enough to select the right action. However, there is no explicit when-to-use vs. when-not guidance and no alternative named (e.g., sys_info for machine stats or shell_exec for arbitrary commands), leaving the routing to inference.

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