Start async focus trace

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

Annotations are all false (not read-only, not idempotent), so description adds value by disclosing non-blocking nature, ring-buffering with maxSamples, and optional record binding. Could mention that samples overwrite when buffer full or that stopping is required.

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?

Two sentences front-load purpose, then provide key behavioral details (non-blocking, buffer, binding). No unnecessary words or repetition of schema fields.

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?

With output schema present, return values need not be described. Description covers core behavior, optional binding, and default interval. Lacks mention of prerequisites (valid serial/displays) or lifecycle (requires stop tool), but acceptable for a focused start action.

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 coverage is low (20%), but description adds meaning: 'logical displays', 'non-blocking', 'ring-buffered', and 'maxSamples' clarifies buffer behavior. Bound record alignment explained. However, some parameters (serial, displayIds) are well-documented in schema already.

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?

Description clearly states 'Start non-blocking focus sampling for logical displays' with specific verb and resource. Distinguishes from sibling tool mobile_focus_trace (which likely represents a different operation like a one-time trace) and pairs with mobile_focus_trace_stop for lifecycle.

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?

Description provides context on optional binding and default behavior but does not explicitly state when to use versus alternatives like mobile_focus_trace (possibly a synchronous variant). No exclusionary guidance or prerequisites mentioned beyond schema hints.

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