Skip to main content
Glama

score_map

Evaluates a saved occupancy map against ground truth, reporting coverage, wall recall/precision, and false-free area; set align=true to search best translation first.

Instructions

Score a saved occupancy map (map_saver .yaml) against a ground-truth map: coverage, wall recall and precision, false-free area. align=true searches for the best translation first. Offline (nav_explore_eval).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "map_yaml": "<map_yaml>",
      "truth_yaml": "<truth_yaml>"
    },
    "name": "score_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
alignNo
map_yamlYes
truth_yamlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does add real value beyond structured fields by disclosing that align=true performs a translation search before scoring (an extra step with cost implications) and that the tool runs offline under nav_explore_eval. However, it says nothing about what happens on mismatched resolutions/frames, whether failures raise errors, or what the result looks like, so it remains partial.

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

Conciseness5/5

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

Front-loaded with the core action and inputs, followed by the metric list and then the one parameter nuance that matters. Every clause earns its place; there is no restatement of the tool name or filler.

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?

For a three-parameter, no-annotation, no-output-schema evaluation tool, the description covers what is scored and the align flag, but leaves the return shape (per-metric values? aggregate score? units?) and error/edge-case behavior entirely undocumented. Adequate to attempt a call, not complete enough to predict results.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate for all three parameters. It partially does: "map_saver .yaml" clarifies map_yaml's expected file type, "ground-truth map" identifies truth_yaml's role, and "align=true searches for the best translation first" explains the boolean's effect. It still omits path semantics, the align=false baseline behavior (default), and the nature of the two required inputs' relationship (same frame/resolution).

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 ("Score") and resource ("a saved occupancy map (map_saver .yaml) against a ground-truth map") and enumerates the computed metrics (coverage, wall recall/precision, false-free area). That combination of input pair and metric set makes it unmistakably distinct from the sibling diagnostics tools (analyze_trajectory, diagnose_slam, ros_graph), which operate on live graphs or motion data.

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

Usage Guidelines3/5

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

Usage context is only implied: the agent can infer it is used after saving a map and having a reference map to compare against, and the "Offline (nav_explore_eval)" tag hints at the evaluation package. There is no explicit statement of when to pick this over other evaluation/diagnostic siblings, no prerequisites (e.g. matching resolution/origin), and no exclusions.

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