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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the description correctly spends no words on safety. It does add genuine beyond-schema context: 'fixed data, re-checked after Facepunch balance patches', the `verified`/`sources_cited` provenance fields, and the notable caveat that logic parts have drawn 0 since April 2024. Since there is no output schema, the return-field enumeration carries real weight, though units and freshness are given without stating how stale data can get or how to check.

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?

Front-loaded with a one-line summary and the canonical source URL, then grouped by returned object (consumers/logic, sources, batteries, mechanics, provenance). Backtick field names keep it scannable. Slightly dense — the parenthetical unit notes could be trimmed — but each clause conveys information an agent would otherwise lack.

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?

With no input parameters and no output schema, the description must substitute for a return-type definition, and it largely does: it lists every top-level field, the sub-fields of consumers and sources, and the units for battery capacity. What is missing is the alternative-route guidance (calculate_power vs. this raw data) and any statement of the data's granularity or completeness.

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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline of 4 applies. Nothing in the description invents or misdescribes an input.

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 ('Electricity data') and enumerates exactly what it returns: consumers, logic, sources, batteries, mechanics, verification metadata. An agent knows this is a reference-data lookup rather than a computation. It stops short of naming the closest sibling (calculate_power), so the boundary with the calculator tools is only implied by 'the data behind .../calculators/electricity'.

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?

Usage is implied rather than stated: by calling itself 'the data behind' the electricity calculator it signals 'use me for raw reference values, not for computing a base'. There is no explicit when-to-use, no when-not-to-use, and no pointer to calculate_power or get_data_freshness as alternatives.

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