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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely new behavioral context — results are paged, and each record includes totals plus the open amount — which matters when there is no output schema.

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 compact sentences: the filter inventory first, the paging/return note second. Every clause carries information and nothing is padded.

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, 15-parameter list tool with no output schema, the description covers the filter dimensions and the shape of each returned record (totals, open amount). It does not mention the default page size or pagination limits, though those are documented in the schema, leaving only minor gaps.

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% across all 15 parameters, and the schema documents formats, defaults and constraints (e.g. yyyy-mm-dd dates, status pattern, per_page bounds) in more detail than the description. The description only restates a subset of filter dimensions, adding no syntax beyond the schema, so the baseline of 3 applies.

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 invoices (Rechnungen)') and enumerates the filter dimensions (client, status, number, date range, text, tags), so an agent immediately knows what the tool returns. It does not explicitly distinguish itself from near siblings like billomat_list_invoice_items or billomat_list_recurring_invoices, but the resource is unambiguous.

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 filter list implies when the tool is useful, and the clause 'each invoice carries totals and the open amount' hints at why one would list rather than fetch a single invoice. However, no alternative (e.g. billomat_get_invoice, billomat_invoice_totals) is named and no when-not guidance is given.

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