native_scene_read

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

With no annotations, the description carries the full burden and does substantial work: it discloses the bridge-plugin dependency, explicitly states 'no desktop input occurs' (i.e., no side effects on the desktop), and warns that the revision is not a full mesh-content hash. It stops short of plainly declaring the operation read-only or describing staleness/repeat-read behavior, but the caveats about copied data and the revision's limited meaning are genuinely useful.

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?

The core purpose is front-loaded in the first sentence, and the two follow-on clauses (revision caveat, plugin prerequisite) each add distinct information rather than restating the name. Some phrasing is dense ('copied live scene identities/poses/settings'), but no sentence is wasted.

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 required; the description instead supplies the prerequisite and the key semantic caveat an agent needs to interpret results correctly. What remains missing is only sibling routing and an explicit read-only statement.

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 nothing for the description to disambiguate and the baseline is 4. The notes about what 'revision' means still add interpretive value for consuming the response.

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 states a specific verb (read) and a specific resource set (live scene identities, poses, settings, and an observed revision), so the agent knows this is a scene-state read rather than a transform/history/text op. It does not, however, name or contrast itself with close siblings like native_transform, project_geometry_read, or host_snapshot, so differentiation is inferred from the name rather than stated.

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?

'for typed GUI edits' hints at the intended context, and 'Requires the running official bridge plugin' gives a concrete prerequisite. But it never says when to prefer this over native_transform, native_ui_capabilities, or the project_* read tools, nor when not to use it, leaving alternative selection to inference.

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