Ridge Pack

Building regulations, Part L and planning flags

check_building_regs

Read-onlyIdempotent

England and Wales. Says whether a roofing job is notifiable to building control (re-covering 25% or more of a roof, a change of covering, structural work, rooflights, dormers, solar, new roofs), whether Part L wants the whole roof insulated (England: more than 50% of the roof or more than 25% of the whole envelope renovated, target 0.16 W/m2K from Approved Document L; Wales: over 25%), who signs it off (competent person scheme such as CompetentRoofer, or building control), and flags for listed buildings, conservation areas, Article 4, flats, bats and asbestos. Each answer cites the official source. Typical call: {"nation":"england","work_type":"re_cover_pitched","percent_of_roof":100,"insulation":"ceiling_level","competent_person_scheme_member":true}.

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": {
      "work_type": "<work_type>"
    },
    "name": "check_building_regs"
  }
}

Input Schema

Name	Required	Description
`trade`	No	Optional. The roofer's own business details (Nero Trade Profile v1). Used to put the contractor on risk notes and to give a stable nero_trade_ref. Not stored by Ridge Pack.
`nation`	No	Default england.
`work_type`	Yes
`insulation`	No	Where the roof insulation is or will be.
`building_use`	No	Default dwelling.
`listed_building`	No
`percent_of_roof`	No	Share of this roof's area being stripped, re-covered or repaired, 0 to 100. Needed for re-covering and repairs.
`built_before_2000`	No	For the asbestos flag.
`conservation_area`	No
`flat_or_maisonette`	No
`article_4_direction`	No
`fire_performance_changes`	No
`percent_of_whole_envelope`	No	Optional: share of the whole building envelope (walls, roof, floor) being renovated, for the major renovation test.
`changes_external_appearance`	No	Will the roof look noticeably different?
`competent_person_scheme_member`	No	Is the roofer registered with a roofing competent person scheme (for example CompetentRoofer)?
`new_covering_weight_change_percent`	No	How much heavier (+) or lighter (-) the new covering is, percent.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, and the description adds real substance on top: the jurisdictional scope limit, the concrete regulatory thresholds applied (25% re-cover, >50% roof / >25% envelope renovation, 0.16 W/m2K), and that every answer cites the official source. It does not describe the response structure or what happens with ambiguous inputs, which keeps it off 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?

Jurisdiction and purpose are front-loaded in the first few words, and the dense middle sentence earns its length by listing triggers and thresholds. The appended example call is genuinely useful for invocation, though the single run-on paragraph could be broken up for faster scanning.

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

Completeness4/5

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

For a 16-parameter, nested-object compliance tool with no output schema, the description covers the domain, thresholds, sign-off logic, and a worked example, which is enough to call it correctly. The remaining gap is that an agent gets no sense of the answer's structure beyond 'cites the official source', which would matter for chaining into a report.

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?

With 63% schema coverage across 16 parameters, the description compensates by tying several inputs to their decision role: percent_of_roof against the 25% test, the envelope share against the major-renovation test, insulation placement against Part L, scheme membership against sign-off route, and the listed/conservation/Article 4/flats/bats/asbestos flags. The nested trade object and fields like fire_performance_changes or new_covering_weight_change_percent are left to the schema, so it is not exhaustive.

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?

Names a specific decision resource ('says whether a roofing job is notifiable to building control'), its jurisdiction (England and Wales), and enumerates the exact determinations it returns: notifiability, Part L insulation trigger, sign-off route, and planning flags. This is clearly a compliance-advice tool and cannot be confused with siblings like roof_takeoff or check_pitch_headlap.

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?

The description makes the use case explicit by listing the work types that trigger a call (re-covering 25%+, change of covering, structural, rooflights, dormers, solar, new roofs) and supplies a concrete typical call. It stops short of stating when not to use it or naming an alternative sibling for out-of-scope questions (e.g. pitch/headlap queries).

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

All Ridge Pack tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.