Calculate Power Usage Effectiveness (PUE) for a data centre or server room. Returns PUE score, efficiency rating, annual cost estimate, and engineering recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| cooling_kw | Yes | Total cooling system power in kW. Example: 200 | |
| it_load_kw | Yes | IT equipment power draw in kW. Example: 500 | |
| lighting_kw | Yes | Lighting power in kW. Example: 1.5 | |
| ups_losses_kw | Yes | UPS and power distribution losses in kW. Example: 25 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
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 does disclose that this is a calculation that returns PUE score, efficiency rating, annual cost estimate, and engineering recommendations. However, it omits behavioral details such as assumptions behind the annual cost estimate or the efficiency rating scale, which could matter for interpreting results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the operation and scope, then lists all expected outputs. Every phrase earns its place with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple calculator nature and fully documented parameters, the description is largely complete: it states what it calculates, for whom, and what it returns. It could be improved by explaining the efficiency rating scale and cost assumptions, but these are minor gaps for a low-complexity tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and each parameter already includes a description and an example. The tool description adds no parameter-level semantics, but none are needed because the schema fully documents all four required inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('Calculate'), names the exact metric and scope ('Power Usage Effectiveness (PUE) for a data centre or server room'), and lists four concrete return components. This clearly distinguishes it from sibling tools like estimate_cooling_load or thermal_load.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear use context—data centres and server rooms—which tells an agent when this tool is relevant. It does not explicitly name alternatives or exclusions, but the domain context and unique PUE scope are sufficiently clear given the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools have distinct domains (structural, carbon, compliance, heat pumps), but several overlap at a surface level: calculate_carbon, building_carbon_footprint, and uae_climate_ghg all deal with carbon; estimate_cooling_load and thermal_load both compute cooling loads; and multiple UK/UAE compliance checkers have similar 'readiness/checker/precheck' names. Descriptions help differentiate, but an agent could still select the wrong tool without careful reading.
Naming is a mix of verb-led patterns (assess_epbd_score, calculate_carbon, check_uae_bim_compliance, estimate_cooling_load, get_technical_dd_quote) and noun-led phrases (building_carbon_footprint, building_readiness, digital_renovation_passport, roi_calculator, thermal_load). Sub-groups like check_* and eurocode_* are consistent internally, but the overall set has no unifying convention, which adds cognitive load.
With 27 tools, the server exceeds the 'heavy' range, even though the engineering domain is broad. Many tools are highly specialized (e.g., part_s_ev, mees_checker, dgnb_bim_readiness), and the large count risks overwhelming an agent trying to pick the right one. The scope may justify the number, but it edges into too-many territory.
The server covers a wide range of building and sustainability assessments: carbon, energy, compliance (EU/UK/UAE), structural design, cost benchmarking, and data centres. However, there are gaps in adjacent areas common to building engineering—such as acoustic design, water/sanitation, electrical systems, or thermal bridging—which would be expected from a general 'engineering' server. It is reasonably complete for its apparent sustainability/regulatory focus, but not universally.
