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

Annotations indicate non-read-only, non-idempotent, non-destructive behavior, so the description adds significant value by disclosing that the trace is a diagnostic, not a replayable script, with specific truncation limits and a maximum entry count. It also explains that CDP payloads carry session-scoped ids that are meaningless in a later session, which is crucial context beyond the annotations. Minor gap: it does not mention potential performance impact of continuous recording.

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 front-loaded with the primary action, followed by scope, then usage guidance and limitations. Every sentence is informative and necessary; no fluff or repetition.

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 complexity of a recording tool with no output schema, the description covers the essential aspects: what is recorded, how to stop, limitations (truncation, entry cap), and why it's diagnostic rather than replayable. It also cross-references the alternative (flow recording) for replay use cases. This is complete for an agent to make an informed decision.

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 both parameters (udid, label) are fully documented in the schema. The description adds no extra semantic detail about the parameters, so the baseline score of 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?

States a specific verb (Start recording) and resource (every Web Inspector / CDP command and event for a device), with additional detail on what is captured (sent, returned, timing). The description also names the paired stop tool (ios_safari_record_stop) and distinguishes it from flow recording (which captures selectors) for replay, clearly separating it from sibling tools.

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 when-to-use guidance: 'use flow recording (which captures selectors) when you want playback' versus the diagnostic purpose here. The tool's scope is delineated ('Spans all Safari tool calls until ios_safari_record_stop'), and the description warns that payloads are truncated and the trace stops appending after 50,000 entries, which are important operational limits for deciding whether to use this tool.

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