ui_snapshot

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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds real value by disclosing that pages are immutable and can be re-read without touching the device — a non-obvious caching semantic — but it omits that visible_only and controls_only default to true and will silently filter the tree, and says nothing about node/page caps or failure modes.

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 compact sentences, each carrying distinct information — capture semantics, paging semantics, and output shaping — with no filler. It is front-loaded with the core action rather than burying it.

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?

An output schema exists, so return-value explanation is not needed. But for a 13-parameter tool with 0% schema coverage, the description leaves the default filtering behavior (visible_only/controls_only=true) and the bounding knobs unexplained — an agent could easily misread a filtered snapshot as complete.

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 0%, so the description carries the burden and does explain the most consequential params: snapshot_id + offset for immutable paging, include_text as opt-in, and format=detail/fields for extra metadata. That leaves eight parameters (depth, limit, max_nodes, visible_only, controls_only, root_view_id, device_id, session_id) with no semantic help beyond their bare titles, so compensation is partial.

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 a fresh bounded UIKit summary.' The word 'bounded' and the pagination note distinguish it from a raw dump, though it never names how it differs from sibling ui_capture or ui_automate.

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?

It gives one concrete usage pattern (reuse snapshot_id + offset to page without device access) and notes text is opt-in, which implies when to set include_text. But it offers no explicit when-to-use vs. ui_capture/ui_automate guidance and no prerequisites for device_id/session_id.

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