get_screen_fingerprint

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

With no annotations, the description carries the full burden. It does add real behavioral context beyond the schema: returns evidence metadata with acquisition intervals, 'conservative freshness', and a genuine timing caveat that device log times are not comparable with host dispatch times. However it omits permissions/device prerequisites, latency, what makes a fingerprint unstable, and what the returned evidence actually contains.

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?

Four dense sentences, front-loaded with the core action before the parameter and timing caveats. A few phrases are vague jargon ('conservative freshness', 'collect independently') that cost clarity without obvious payoff, but nothing is padded.

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?

There is no output schema and no annotations, so the description is the only source of truth for returns. It gestures at 'evidence metadata with acquisition intervals' but never describes the fingerprint's shape or the evidence fields, leaving an agent unsure what it will actually receive from a nested-parameter 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 67% and the description fills the most important gap: it explains that actionRef links a known same-session/device action and that unavailable references simply collect independently, which the nested schema (sessionId/actionId only) does not convey. deviceId and platform already carry their own schema descriptions, so this is a meaningful but not exhaustive add.

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 concrete verb and resource: 'Generate a stable fingerprint representing the current visible screen (activity + visible UI elements)'. That is more specific than a bare name restatement, but it never contrasts itself with near-neighbors like get_current_screen, get_ui_tree or capture_screenshot, so an agent still has to infer which of those to pick.

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?

There is no explicit when-to-use, when-not-to-use, or named alternative anywhere in the text. The only usage-adjacent content is the actionRef note about linking a known action or collecting independently, which explains one parameter's behavior rather than tool selection.

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