list_processes

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

Without annotations, the description is the only source. It mentions cross-platform compatibility and that results are filtered/sorted. However, it doesn't disclose potential system impact, permission requirements, or performance characteristics. Adequate but could be richer.

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?

Three sentences, each adding value: what it lists, cross-platform support, and behavior. Front-loaded with the core purpose. No redundancy.

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 main functionality and mentions output format (formatted table). With an output schema present, return value details are not required. However, it omits default behavior (lists all processes) and scope (e.g., only user processes or all). Very close to complete for a simple tool.

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?

Input schema already fully describes both parameters (filter_name and sort_by). The description adds no new parameter information beyond 'filtered and sorted as requested'. Baseline 3 is appropriate given 100% schema coverage.

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 clearly states the tool lists running processes with specific fields (PID, name, CPU%, memory usage). It distinguishes itself from sibling tools like kill_process or start_process by being a read-only listing tool.

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?

No guidance on when to use this tool versus alternatives like kill_process or execute_command. Does not specify when the output might be useful or any prerequisites.

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