list_processes

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

The description adds significant context beyond annotations: it states the tool is read-only (consistent), explains what data is returned, describes rare outcomes (empty result), and documents error conditions (no trace loaded). Annotations already mark it as read-only and non-destructive.

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 well-structured with clear sections and front-loaded information. It could be slightly more concise by removing 'Read-only.' since annotations already convey that, but overall it efficiently delivers value.

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 output schema, the description thoroughly covers return fields, edge cases, and error scenarios. It fully prepares the agent to use the tool correctly and understand its results.

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?

The description claims 'Parameters: none — operates on the loaded trace', but the input schema includes an optional 'trace_id' parameter. This is a direct contradiction between description and schema, misleading the agent about available parameters. Despite 100% schema coverage, the description undercuts clarity.

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 enumerates the fields returned. This explicitly identifies the tool's function and scope, distinguishing it from siblings that focus on specific Chrome analyses.

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?

Explicit guidance on when to use (entry point for Android/Linux, picking pid) and when not to (Chrome traces), with specific alternative tools mentioned (chrome_* tools).

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