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

Annotations already declare readOnly/destructive/openWorld, so the bar is lower, yet the description adds real behavior: sort order (oldest due date first), page size (up to 100) and cursor round-trip, plus an auth prerequisite (Cotlet key with app access). Nothing about limits or error cases, hence not a 5.

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?

'oldest due date first' is stated twice and the opening phrase 'Holded: Sales invoices with number, client, total...' is a fragment duplicated by the following full sentence, which wastes space. The pagination and auth details are front-loaded acceptably, but the redundancy costs it.

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 output schema, the description carries the return-value burden and does so by listing the fields each item shows (total, open amount, draft flag), and it covers pagination and auth. Complete enough for a read-only list tool, though status/filter interplay could be tighter.

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%, so the baseline is 3. The description restates the status enum and cursor mechanics, but those are already documented in the schema, adding only marginal value (that next_cursor is passed back as cursor).

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+resource (lists sales invoices) and enumerates the returned fields and ordering, which is far from a tautology. It does not explicitly differentiate itself from siblings like holded_list_purchases or holded_get_invoice, so it stays just short of 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?

Gives concrete usage context: 'Filter by contact, issue date or due date to find what is late' and explains the status semantics (unpaid = pending+overdue). There is no explicit when-not or naming of an alternative tool, so no 5.

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