list_processes

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

Discloses read-only nature, no parameters, empty result case (rare), and error when no trace loaded. No annotations provided, so description fully covers behavioral expectations.

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?

Concise with clear sections for usage, limitations, errors. Every sentence adds value without 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?

Despite no output schema, description explains return fields and fully captures usage context, preconditions, and error scenarios.

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?

No parameters, so baseline is 4. Description adds that it operates on the loaded trace, which is useful context beyond the empty schema.

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?

Clearly states it lists processes with fields (upid, pid, name, start_ts, end_ts) and distinguishes from Chrome-specific tools by noting it's for Android/Linux traces.

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?

Explicitly states when to use (entry point for Android/Linux trace analysis, picking pid/upid for other tools) and when not to use (Chrome traces, recommending dedicated chrome_* tools).

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