PyNet Bridge

Overview Schema Source Related Servers Discussions Admin

viewer_highlight_clash

Destructive

Highlights clash pairs in the viewer by coloring elements A red and B green, isolating all others. Accepts single IDs or lists per side for multi-clash review.

Instructions

Highlights a clash (element(s) A red, element(s) B green) and isolates the rest away.

Usually one pnt_id per side (a single clash pair), but either side accepts a list — e.g. one element (A) against every counterpart it clashes with (B), all shown at once.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pnt_id_a`	No
`pnt_id_b`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.5.6Oct 2, 2026

addedInput schema / properties / pnt_id_a / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / pnt_id_a / type
```
Removed value: -"string"
```

addedInput schema / properties / pnt_id_b / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / pnt_id_b / type
```
Removed value: -"string"
```

Addedv1.1.0Jul 15, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations supply only destructiveHint=true; the description adds genuinely new behavioral context: the red/green coloring, that everything else is isolated away (which explains the viewer-state mutation behind the destructive hint), and that lists are accepted on either side. It does not discuss whether the prior view state is recoverable, but it substantially enriches the thin annotation set.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action and color mapping, then the cardinality nuance. No wasted wording, though the parenthetical list example is slightly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values need no explanation, and the parameters are covered. What is missing is routing guidance against the many viewer_* siblings and any note on how destructive the isolation is to the current view state.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and neither pnt_id_a nor pnt_id_b is described in the schema, but the description compensates well by mapping A to red and B to green and clarifying the string-or-list shape of both. This is close to the full meaning an agent needs, though it never explains what a pnt_id refers to.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (highlights) and resource (a clash), plus the exact visual semantics — element(s) A red, element(s) B green — and the side effect of isolating everything else. An agent can distinguish this from viewer_isolate and viewer_select on the color/isolate behavior alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains how the parameters behave (one id per side vs a list) but never states when to reach for this tool instead of viewer_isolate, viewer_select, or viewer_list_clashes. No prerequisites or exclusions are given.

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