list_processes

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. The description adds context: 'Read-only', empty result rarity, and error conditions (no trace loaded). No contradictions.

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?

The description is concise, using bullet points and front-loading the main action. Every sentence is informative 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?

Given no parameters, output schema, or complexity, the description covers purpose, usage boundaries, results, and error handling completely. No 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?

No parameters exist, and schema coverage is 100%. The description explicitly states 'Parameters: none — operates on the loaded trace', which adds clarity beyond the 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?

The description clearly states 'List every process captured in the trace' and lists the fields (upid, pid, machine_id, etc.), making the tool's purpose distinct. It explicitly differentiates from sibling Chrome tools by advising against use for Chrome 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?

The description provides explicit when-to-use ('entry point for Android and Linux trace analysis') and when-not-to-use ('Chrome traces — use chrome_* tools') guidance. It also mentions a prerequisite ('call load_trace first').

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