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

No annotations are provided, so the description carries the full burden. It discloses the sampling window nature, that FPS is passive (reflects current on-screen content rather than driving anything), and that utilization metrics are conditional ('when available'). It does not describe the return format details or potential failure modes, but the key behavioral characteristics are covered.

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 three sentences and information-dense. Each sentence earns its place: sentence 1 states purpose and returns, sentence 2 differentiates from siblings, sentence 3 covers prerequisites and usage context. Slightly longer than strictly needed but no wasted words.

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 two-parameter tool with 100% schema coverage and no output schema, the description covers purpose, return values, platform restriction (physical device), session requirements, and the practical caveat about driving the app first. The only gap is lack of description of the output structure/format, though no output schema exists to compensate for that.

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 the schema documents both parameters (udid, durationMs with min/max/default). The description adds meaningful context beyond the schema by explaining the durationMs is a 'short window' and that FPS reflects current on-screen state, which relates parameter semantics to tool behavior. It doesn't enumerate parameters explicitly but the schema already handles this well.

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 uses a specific verb+resource ('Sample on-device rendering FPS for a physical iOS device') and specifies the exact return values (mean/min/max FPS plus GPU/renderer/tiler utilization when available). It clearly distinguishes itself from sibling tools by explicitly naming android_fps as its iOS counterpart.

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?

The description provides clear context: 'No automation session required' and explains that FPS reflects 'whatever is on screen during the window' with guidance to 'drive the app first for a meaningful reading.' It stops short of explicitly naming alternatives or when-not-to-use, but the context is strong and self-contained.

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