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

With no annotations provided, the description carries the full burden, and it delivers well: it discloses scope-screening behavior, the four KPIs computed, and adds the crucial caveat that 'the regulation mandates reporting, not target values' — preventing the agent from misreading outputs as compliance verdicts. It does not disclose handling of missing optional inputs or return format, but the core behavioral profile is honestly and usefully stated.

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?

Three sentences, zero filler: legal identity, core functionality, and a high-value caveat. Each sentence earns its place, and the functional verbs appear immediately after the legal framing.

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?

No output schema exists, so the KPI list and scope-determination statement give the agent a solid expectation of what the tool returns. Missing details — return format and behavior when optional inputs are absent — are minor for a stateless calculation tool whose inputs are fully self-documented.

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 the schema already maps parameters to KPIs ('WIN: total water input (m3/yr), for WUE', 'EREUSE waste heat reused, for ERF'). The description adds the 500 kW threshold context for it_power_kw and the KPI acronym list, but this is marginal value over the schema — the baseline 3 is appropriate.

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 names a specific resource ('data-centre reporting pack') with explicit verbs: 'determines reporting scope' and 'computes the mandated KPIs PUE, WUE, ERF and REF'. The EED legal citations plus the enumerated KPI set clearly differentiate it from siblings like calculate_pue, which handles only a single KPI.

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?

Clear context is established via the legal basis (Dir (EU) 2023/1791 Art.12 + Del. Reg (EU) 2024/1364) and the applicability threshold ('IT power >= 500 kW'), which tells an agent when this tool is the right choice. It does not explicitly name alternatives or state when-not-to-use, but the regulatory framing makes the intended scenario unambiguous.

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