Skip to main content
Glama
asedias

bl-mcp

by asedias
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

walkable_map

Read-only

Check where an agent of a given size can walk in a 3D level. Flood from a start point and return reachable, unreachable, and blocked areas to verify connectivity.

Instructions

Check where an agent of this size can walk, then flood from start (default: the largest area). Floors are found by rays, so ramps, stairs and several levels work. Returns the reachable, unreachable and blocked areas in m2 and a top-down image. largest_regions gives each region's area, whether it is reachable, its floor height range and its box: an unreachable region with a high floor_z is a roof or a crate top, not a design error. Use it to prove that every room, spawn and objective connects. probe is a list of world points: for each the answer gives walkable, reachable, floor_z and free_width_m (the widest agent that fits there), so a spawn, a site or a chokepoint can be checked by number.

Input Schema

NameRequiredDescriptionDefault
cellNo
namesNo
probeNo
startNo
max_stepNo
max_levelsNo
agent_heightNo
agent_radiusNo
max_slope_degNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / cell / anyOf
      Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / cell / default
      Previous value: -0.5New value: +null
    • removedInput schema / properties / cell / type
      Removed value: -"number"
    • addedInput schema / properties / probe
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "items": {
+          "type": "number"
+        },
+        "type": "array"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  2. First observedv0.4.0

TDQS

A3.8/5.0
Behavior5/5

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

Beyond the readOnly/non-destructive annotations, the description discloses how floors are derived (rays, so ramps/stairs/multiple levels work), what the response contains (areas in m2, a top-down image, largest_regions fields), and even interpretation guidance (an unreachable high floor_z region is a roof or crate top, not a design error). This is exactly the extra behavioral context annotations cannot provide.

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?

The core action and defaults are front-loaded, and the probe behavior follows in a logical second block. It is dense and slightly long, but the length is defensible for a 9-parameter spatial analysis tool with no output schema.

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?

With no output schema, the description does a good job explaining return values (m2 areas, image, largest_regions and probe field meanings). However, for a 9-parameter tool at 0% schema coverage, the missing parameter semantics leave a real gap in what an agent needs to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is 0% across 9 parameters, so the description must carry the burden. It meaningfully explains `start` (defaults to the largest area) and `probe` (list of world points returning walkable/reachable/floor_z/free_width_m), and "an agent of this size" hints at the agent dimensions. But cell, names, max_step, max_levels, agent_height, agent_radius and max_slope_deg are never addressed, leaving most parameters opaque.

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

Purpose4/5

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

The description gives a specific verb and resource: it checks walkability by flooding from a start point and returns reachable/unreachable/blocked areas plus an image. The purpose is unmistakable and conceptually distinct from siblings like viewshed or sightline_map. It stops short of explicitly naming an alternative, so it lands just under a 5.

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

Usage Guidelines4/5

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

"Use it to prove that every room, spawn and objective connects" states a concrete use case, and the probe paragraph explains a second scenario (checking a spawn, site or chokepoint by number). There is no explicit when-not-to-use or named alternative tool, so it is clear context without exclusions.

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

Deploy Server

Other Tools