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

Annotations already establish readOnly/idempotent/non-destructive safety, and the description adds value beyond them by disclosing the return payload ('the rule and its source') and the hard-coded calculation rule with an effective date. It does not contradict any annotation.

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?

A single sentence with no filler, and the core rule is stated up front. The heavy parenthetical makes it slightly harder to scan, but nothing is wasted.

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, but the description names what is returned (rule plus source), covering the main return-value gap. It is thin on behavior for invoices dated before 1 October 2026 and on the exact output shape, which keeps it from a 5 for a tool with no structured return contract.

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 coverage is 100% (invoice_date, format YYYY-MM-DD), so the baseline would be 3. The description goes further by tying the parameter to the invoicing month-end rule and the 1 October 2026 threshold, giving the date input meaning the schema alone does not convey.

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 the specific resource (monthly EDF due date for a services export invoice) and encodes the actual computation rule (30 days from month-end of invoicing, effective for invoices from 1 October 2026), so an agent knows exactly what is produced. It stops short of naming the closest sibling, export_realisation_deadline, so it doesn't fully disambiguate the two deadline tools.

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 'for invoices from 1 October 2026' clause implicitly scopes applicability, which is useful selection context. However, there is no explicit when-to-use/when-not-to-use statement and no routing to the sibling deadline tool, so applicability before October 2026 is left to inference.

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