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

Discloses that the tool captures live logs for a few seconds and returns lines, and that unfiltered captures are mostly noise. It mentions no automation session is required. With no annotations, the description carries full burden; it covers the key behavioral traits but does not detail capture timing specifics or output truncation limits.

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?

Description is front-loaded with the core action and immediately clarifies system vs. app logs. It is relatively concise (3 sentences), but the third sentence could be more direct. No wasted words, but slightly more verbose than necessary.

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 the absence of annotations, schema, and output schema, the description is fully complete. It defines the tool's purpose, scope, differentiation from siblings, and usage patterns. The complexity is low, and the description leaves no major gaps for an agent to misinterpret.

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 description coverage is 100%, so the schema already fully documents parameters. The description adds value by explaining the filtering rationale (idle noise) and suggesting practical usage, but does not supplement parameter details beyond what the schema provides. Baseline 3 is appropriate.

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 captures a live system log (os_log/syslog) from an iOS device, specifying it returns lines. It explicitly distinguishes itself from sibling tools like ios_safari_console_logs (for web pages) and lists specific use cases: crashes, permission denials, and app startup failures.

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?

Provides explicit guidance on when to use (debugging device-level issues) and when not to (app console logs, which points to ios_safari_console_logs). Offers concrete filtering advice using `process` and `contains` to avoid noise from idle devices, and suggests running the target action during capture or immediately after.

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