ui_snapshot

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

Annotations already show readOnlyHint=true and destructiveHint=false; the description adds useful behavioral context: it operates on the 'RUNNING game', returns semantic state that pixels cannot convey, and includes 'per-control honesty flags'. This goes beyond the annotation bare minimum without contradicting them.

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?

Dense, information-rich and mostly front-loaded with purpose and usage guidance. The trailing sentence 'Every field, and the free since_hash re-read: help(tool="ui_snapshot")' is awkwardly phrased and slightly cryptic, but the overall length is justified by the amount of useful routing 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?

Despite having no output schema, the description enumerates the core return contents and semantic fields, and the schema covers all 5 parameters. It could be more complete by describing the shape of a returned snapshot or what 'honesty flags' mean, but an agent can confidently select and call this tool for functional UI checks as written.

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?

Input schema has 100% description coverage, and every param is individually documented (path, max_nodes, occlusion, since_hash, interactive_only). The description adds only a small extra note about 'free since_hash re-read', so it does not meaningfully extend what the schema already communicates.

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 clearly identifies the tool's purpose: a 'one-call UI snapshot of the RUNNING game' returning visible Controls as structured data, with an explicit list of fields (path, class, text, rect, semantic state, honesty flags). It also distinguishes it from screenshot and names the composite workflow it replaces, so an agent can differentiate it from siblings.

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?

Provides explicit usage guidance: 'For FUNCTIONAL UI checks this replaces screenshot + find_ui_elements + get_control_rect + runtime_get_property; keep screenshot for visual/render bugs.' This directly answers when to use this tool versus alternatives and even gives an exclusion case.

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