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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive, closed-world), so the description's added value is the disclosure that criteria are returned as true, false or null when not yet known, plus the returned keys generation, demand, facts_to_put_on_the_form, missing_facts and sources. It also explains that facts are prefilled from inputs and trade, which tells the agent the call has a side benefit. It does not discuss rate limits, or what happens with incomplete or contradictory equipment data, so it stops short of 5.

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?

It is front-loaded with the decision, then the generation branch, then the demand branch, then the return shape, then a worked example, so structure mirrors how the agent will use it. The prose is dense and long, and a short bulleted split of the three regimes would be faster to parse, but no sentence is 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?

For a 20-parameter nested-schema tool with no output schema, the description carries the decision logic, the return keys and the null-criterion semantics, which is a lot of the load. The example maps inputs to the schema shape, reinforcing that. Gaps are minor: it does not explain what happens on northern_ireland, or how conflicting inputs (e.g. max_demand_after_a above the cut-out rating) are resolved.

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 80%, so the schema already carries most parameter meaning, including rating_kw units and the type_tested flag. The description adds two genuinely useful pieces of semantics beyond the schema: existing generation and battery inverters must be counted, and trade feeds prefilled form facts. With 20 parameters and multiple nested objects, one sentence of parameter guidance does not compensate much, so the baseline of 3 holds.

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 states a concrete verb and outcome ('says which network operator process applies and when') scoped to specific equipment types and jurisdiction (Great Britain). It names the actual regimes it decides between (G98, G99, ENA EV charge point and heat pump form), so an agent can tell this apart from check_part_p, check_certificate or size_cable without opening a schema.

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?

It gives clear conditions for each outcome path: G98 applies when fully type tested at 16 A / 3.68 kW per phase or less (install then notify within 28 days), G99 applies when you must apply and wait, and the demand route applies when every criterion is met. It never names a sibling tool to use instead, so there is no explicit exclusion guidance, but the ambiguity the guidance needs to resolve is domain-side and it resolves it.

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