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

Annotations already carry the safety profile (readOnly, non-destructive, non-open-world), and the description adds genuinely useful operational context: bounded duration of a few seconds, the fact that an idle device emits hundreds of lines/second so unfiltered capture is noise, and that no session is needed. It does not describe return shape or failure modes if the device is unreachable. Note: idempotentHint=true is questionable for a live capture, but the description does not assert idempotency, so this is an annotation quirk rather than a contradiction.

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?

Five short sentences, front-loaded with the purpose, then disambiguation, then filtering guidance, then timing, then the session note. Every sentence adds decision-relevant information and none restates the title or schema.

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?

For a 5-parameter capture tool with no output schema, the description covers what it does, when to run it, how to filter, and roughly what comes back ('return the lines'). It stops short of describing the response format (line array vs. text, truncation behavior) and the 60s cap, which the schema covers but the agent must still discover.

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 baseline is 3, but the description goes beyond the schema by naming the two filter parameters (`process`, `contains`) and supplying the rationale that filtering is required to avoid noise on an idle device. `level` and `seconds` are left entirely to the schema, which documents them adequately.

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?

States a specific verb and resource ('Capture the iOS device's live system log ... return the lines') and pins down what the log contains (os_log/syslog: launch crashes, permission denials, startup failures). It explicitly disambiguates from the closest sibling, ios_safari_console_logs, so an agent can choose correctly without opening either schema.

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?

Gives explicit when-to-use conditions (debugging crashes on launch, permission denials, app startup failures), names the alternative for web content, prescribes filtering via `process`/`contains` and explains why, and states the timing rule ('run the action you want to debug WHILE the capture is running'). It even removes a prerequisite ambiguity with 'No automation session required.'

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