host_snapshot

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

There are no annotations, so the description carries the burden; 'Read live' does imply a non-mutating, uncached read of current host state, which is useful context. However, it says nothing about connection requirements, latency, or whether 'dirty states' reflect unsaved in-memory changes versus persisted state.

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?

A single compact sentence with the verb front-loaded and every listed field earning its place. It is a fragment rather than a full sentence, but that costs no clarity.

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 the return shape need not be described, and there are no parameters to document. What remains missing is the operational context for an aggregate 'live' read: whether a host must be attached and what happens when it is not.

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?

The tool takes zero parameters, so there is no parameter semantics gap and the baseline of 4 applies. The description correctly adds nothing about arguments because none exist.

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?

Uses a specific verb ('Read') and enumerates the exact payload: app version, dirty states, selected presets, scene object count. This clearly separates it from single-resource readers like native_scene_read or host_presets_list, though it never names those siblings explicitly.

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?

No guidance on when to prefer this aggregate snapshot over the individual sibling readers (native_scene_read, host_presets_list, host_bridge_status) or on preconditions such as a live host connection. Usage must be inferred from the field list alone.

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