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

Annotations already declare readOnly/non-destructive/idempotent, so the safety bar is lower. The description adds genuinely useful behavior: it requires a physical device, samples over a short bounded window, and notes GPU/renderer/tiler utilization is only available 'when available' — a meaningful caveat about partial results.

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?

Three tight sentences with the tool's function front-loaded, followed by the return shape, the session-independence note, and the prerequisite caution. No filler; every sentence carries distinct information.

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?

No output schema exists, and the description compensates by enumerating the returned metrics (mean/min/max FPS plus GPU/renderer/tiler utilization). Combined with the physical-device requirement and the on-screen caveat, an agent has everything needed to invoke and interpret this tool.

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 100%, so udid and durationMs are already documented with bounds and a default. The description only alludes to a 'short window' without adding format or default details beyond the schema, so baseline 3 applies.

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 (sample), resource (on-device rendering FPS via Core Animation), and the exact metric set returned. It explicitly names android_fps as the counterpart, so an agent can distinguish this iOS tool from its sibling without opening the 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 real usage context: 'No automation session required' and 'drive the app first for a meaningful reading.' It does not spell out when to prefer this over generic performance tools (e.g. ios_performance_snapshot), but the preconditions are clear.

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