Skip to main content
Glama
IBM

chuk-mcp-her

Official
by IBM

her_search_scotland

Retrieve records of 320,000+ Scottish heritage sites from Canmore. Filter by name, site type, location, or bounding box.

Instructions

Search Scottish NRHE records (320,000+ sites from Canmore).

Queries the National Record of the Historic Environment for terrestrial archaeological sites, monuments, and buildings in Scotland. Covers 320,000+ records including castles, brochs, cairns, standing stones, churches, and industrial heritage.

Args: name: Site name keyword (partial, case-insensitive) site_type: Site type keyword (e.g. "CASTLE", "BROCH", "CAIRN") broad_class: Broad classification (e.g. "DOMESTIC", "RELIGIOUS") council: Council area (e.g. "Highland", "Edinburgh") bbox: Bounding box as "xmin,ymin,xmax,ymax" in BNG (EPSG:27700) lat: WGS84 latitude for radius search lon: WGS84 longitude for radius search radius_m: Search radius in metres (requires lat/lon) max_results: Maximum results (1-1000, default 50) output_mode: Response format — "json" (default) or "text"

Returns: Matching NRHE records with site type, classification, location

Tips for LLMs: - This covers ALL known Scottish heritage sites, not just designated ones - For designated assets only, use her_search_scotland_designations - For cross-border queries near England/Scotland border, also run her_search_monuments (NHLE) and her_search_aerial (AIM) for English sites - site_type keywords: CASTLE, BROCH, CAIRN, STONE CIRCLE, CHURCH, FORT, CRANNOG, DUN, STANDING STONE, SOUTERRAIN - MapServer max is 1,000 records per request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latNo
lonNo
bboxNo
nameNo
councilNo
radius_mNo
site_typeNo
broad_classNo
max_resultsNo
output_modeNojson

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A4.7/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral details: the dataset size (320,000+ records), the MapServer limit (1,000 records per request), return format options (json/text), and the requirement that radius_m needs lat/lon. This is strong transparency for a search tool, though it doesn't explicitly state how errors or empty results are handled, which prevents a 5.

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 description is appropriately structured with a front-loaded summary, an Args block, a Returns line, and Tips for LLMs. While it is longer than usual, every section provides necessary information for a tool with 10 parameters and no annotations. No redundant sentences are present, though the tips section could be seen as slightly verbose; however, it contains only actionable advice.

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

Completeness5/5

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

Given the tool's complexity (10 optional parameters, no output schema) and the absence of annotations, the description is remarkably complete. It covers what the tool does, what data it searches, parameter semantics, result format, limitations, and alternatives. The only minor omission is a detailed breakdown of the return record structure, but the Returns line gives sufficient context for a search tool.

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

Parameters5/5

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

With 0% schema coverage, the description must fully explain parameters, and it does. The Args section details each of the 10 parameters, including format ('bbox as "xmin,ymin,xmax,ymax" in BNG (EPSG:27700)'), constraints ('radius_m requires lat/lon'), defaults ('max_results default 50'), and available options ('output_mode: json or text'). This goes beyond minimal descriptions and directly compensates for the incomplete schema.

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?

The description clearly states the tool's purpose: 'Search Scottish NRHE records' and specifies the resource (Canmore, 320,000+ sites). It distinguishes from siblings by noting this covers ALL known Scottish heritage sites versus her_search_scotland_designations for designated assets only, and her_search_monuments for English sites. The verb 'search' plus the resource and scope makes the tool's function unambiguous.

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

Usage Guidelines5/5

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

The 'Tips for LLMs' section provides explicit guidance on when to use this tool versus alternatives: 'For designated assets only, use her_search_scotland_designations' and 'For cross-border queries near England/Scotland border, also run her_search_monuments (NHLE) and her_search_aerial (AIM) for English sites'. It also includes practical usage tips like recommended site_type keywords and the maximum result limit.

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