read_ui_snapshot

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral context: no device round-trip, data is a retained (potentially stale) local artifact, and results are paginated. The node-identity caveat warns the agent not to conflate a visual node with a runtime handler, which is genuine misuse-prevention. Missing are defaults/page size behavior and snapshot lifetime/expiry.

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?

Two tight sentences, zero filler, with the core operation front-loaded and the caveat second. Every clause carries information the agent needs.

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?

With no output schema, the description should say more about what a paged result contains (node fields, total count, whether more pages remain). It covers purpose, offline nature and node semantics well, but leaves the return shape and pagination termination behavior to inference for a 4-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 only 25%, with only analysis_project_id described; snapshot_id, limit and offset have no schema descriptions. The description compensates partially by revealing that limit/offset drive node-list paging, but gives no default page size, no note on the 200 cap, and no clarification of what a valid snapshot_id looks like or where it comes from.

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+resource ('read a retained local UI snapshot') plus the sub-operation ('paging its node list'), and the phrase 'without touching the device' separates it from live-device siblings such as capture_ui and perform_ui_action. An agent can identify it 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?

'Retained local ... without touching the device' clearly frames the context in which this tool is the right pick over live capture tools. It stops short of explicitly naming an alternative or stating a prerequisite (that a snapshot must already exist and be retained).

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