suggest_expense_categories

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

Beyond the readOnlyHint annotation, it discloses the actual decision logic: reuse the category previously used for the same supplier (VAT number or name) within 24 months, otherwise fall back to keyword rules on name and description with examples. It also states the return payload (confidence and reason) and explicitly reaffirms that nothing is modified.

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?

Single dense passage that front-loads the purpose, then the algorithm, then the return value in the final clause. The parenthetical supplier-category list (utenze, telefono, software...) is slightly verbose but illustrative rather than wasteful.

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 correctly supplies the return shape (confidence + reason). Combined with the fully documented input schema and readOnly annotation, an agent has nearly everything it needs; only edge-case behavior (no match found, unknown supplier) is left implicit.

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 the schema already explains ids, source, documents and company_id in detail. The description only loosely maps to them ('fatture passive in attesa' vs 'documenti indicati') without adding defaults, formats or precedence rules beyond what the schema provides.

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?

The description names a specific verb and resource: proposing an expense category for pending passive invoices or explicitly supplied documents. It is unambiguous and there is no sibling tool that does anything similar, though it never explicitly contrasts itself with list_pending_received_documents or get_new_document_defaults.

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?

It states the two usage modes -- pending invoices by default, or an explicit set of documents -- and ties them to the ids/documents parameters. It does not say when the tool should not be used (e.g. after documents are already registered) or what the agent should do with a low-confidence result.

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