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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds that results are 'Paged', which is genuine operational context beyond the annotations, but says nothing about page size defaults, total counts, or empty-result behavior (the schema carries next_page guidance).

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?

Two sentences, no filler. The filter list and paging fact are front-loaded, so an agent gets the scope before any detail.

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 read-only list tool with a fully documented 14-parameter schema and annotations covering safety, the description is nearly sufficient — it conveys both the filter surface and the paged nature. Minor gaps: no mention of defaults (per_page=100, order_by ascending) or how to continue paging, though the schema's page description covers the latter.

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%: every one of the 14 parameters has its own description with formats, bounds and cross-references (e.g. client_id from billomat_list_clients). The description merely names filter categories already covered, and notably omits tags, intro, label, article_id, contact_id, per_page and order_by. 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?

States a specific verb and resource ('List delivery notes (Lieferscheine)') and enumerates the filter axes (client, status, number, date range, text) plus the paged return shape. It implicitly contrasts with billomat_get_delivery_note via the plural/paged framing, but never names or differentiates from a sibling explicitly.

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 by 'filtered by ... ' — an agent infers this is the search/enumerate path versus the single-fetch get_delivery_note. However there is no explicit when-to-use statement, no mention of the sibling get tool, and no guidance on which filters combine or are mutually exclusive.

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