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

Annotations only supply readOnlyHint=true, so the description carries the behavioral load and does it well: it warns that without a date filter only the CURRENT year is returned, points to created_period='all' as the escape hatch, and explains pagination via next_page. It could go further on result caps or ordering defaults, but the key trap an agent would otherwise fall into is disclosed.

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?

Front-loaded with purpose, then the two highest-risk behaviors (default year scope, pagination), then enum decoding, then the endpoint. It is dense and occasionally list-like ('VS ...'), but nearly every clause carries actionable 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?

With 16 optional parameters, no required fields and no output schema, the description supplies the scoping caveat, the pagination contract and the enum interpretations an agent needs to call it successfully. It does not describe return payload shape or default result ordering, but the response contents are at least summarized in the opening sentence.

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%, so a 3 is the baseline; the description goes beyond it by decoding enum semantics the schema only lists as strings (estimate = quote, cancel = credit note, reverse_order) and by explaining that 'several allowed' for type. It also clarifies search fields and the next_page-to-page pagination handoff, adding meaning not present in the raw property text.

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 issued documents) plus what each record carries (client, items, totals, payment status), which distinguishes it cleanly from superfaktura_get_invoice and the other list_* siblings. An agent knows immediately this is the paginated collection endpoint for invoices, not a single-document fetch.

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 real selection guidance: how the type parameter routes between ordinary invoices, proformas, quotes, credit notes, etc., how status narrows by payment state, and what search matches. It also names a sibling (superfaktura_list_clients) for obtaining client_id. It stops short of an explicit when-not-to-use statement (e.g., prefer get_invoice for a known number), so it lands at 4 rather than 5.

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