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

Annotations only declare readOnlyHint=true, so the safety profile is already covered. The description adds genuinely useful behavior beyond that: results are newest-first by default, pagination is driven by next_offset, and products/collections/e-Factura status are opt-in payload expansions that change response weight. It omits any note on rate limits or result-count caps, keeping it at 4.

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?

Three sentences, front-loaded with the resource and filter scope, then defaults, then the pagination contract. The parenthetical filter list is dense but each clause corresponds to real parameters. The trailing endpoint URL is marginal but cheap.

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 an 18-parameter paginated list tool with no output schema, the description covers the two things an agent most needs: how ordering defaults and how to page using next_offset from the previous reply. It doesn't state the response envelope or total-count behavior, which matters when there is no output schema, but overall it is sufficient to invoke correctly.

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 already 89% and the schema documents the toggles precisely (draft = only drafts vs only issued). The description still adds value by grouping the 18 parameters into filter families and mapping the optional flags (with_products, with_collects, with_einvoice_status) to what they actually enrich in the reply. Slightly above the baseline-3 case for high coverage.

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?

Names a specific resource (invoices), scopes it to a company, and enumerates the filter families (series, number, dates, client, draft/canceled/collected). An agent can distinguish it from oblio_list_clients/oblio_list_products and from oblio_get_document (single document) by resource alone. It stops short of explicitly contrasting with those siblings, so a 4 rather than a 5.

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?

There is operational guidance for pagination ('Pass next_offset as offset for the next page') and the default ordering, which is real usage help. However, there is no explicit when-to-use statement or exclusion — nothing tells the agent to prefer oblio_get_document for a single invoice or when a filter combination is pointless. Usage is implied by the resource name rather than stated.

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