Documenti ricevuti e spese

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real value: the pending-mode semantics (SDI-received, not yet registered) and an explicit data-trust warning that supplier-written text must be treated as data. It does not describe pagination cost or result shape, which the schema only partly covers via all_pages.

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?

The core scope is front-loaded in the first sentence, with the mode switch and the data-trust note following in logical order. The final English sentence duplicates the first Italian sentence, which is a small amount of redundancy rather than bloat.

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 13-parameter, zero-required listing tool with no output schema, the definition covers scope, the alternate pending mode, filter categories, and a prompt-injection caution. Missing only finer details such as pagination behavior and how the two listing modes differ in the fields returned, which are moderate gaps rather than blocking ones.

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 77% (above the 80% baseline region), so the schema already carries most parameter meaning. The description adds only the meaning of pending and a general mention of period/supplier/description filters, without clarifying precedence rules (date_from/date_to over year/month) or supplier_id vs supplier_name.

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 (lists expenses / received documents) and enumerates the exact document types covered (fatture passive, note di credito passive, DDT passivi, autofatture). It is clearly separable from the singular sibling fic_get_received_document and from the mirror tool fic_list_issued_documents without opening any schema.

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 the operative context (filter by period, supplier, description) and an explicit mode switch: 'Con pending: true elenca invece le fatture elettroniche ricevute dallo SDI e non ancora registrate', which routes the agent between the two behaviors. It does not name a competing sibling (e.g. fic_get_einvoice) or state when this listing should be preferred, so it stops short of a 5.

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