bank_reconcile

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

With no annotations, the description carries the burden well: it discloses that the tool mutates state ('segna come pagate le rate'), that dry_run is the safe preview mode, and how confidence thresholds gate writes. It doesn't address reversibility, permissions, or idempotency, so it stops short of full disclosure.

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?

Two dense sentences with the core purpose and the dry-run workflow front-loaded; little waste. The confidence-threshold clause is slightly compressed but earns its place.

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 9-parameter mutation tool with a nested mapping object and no output schema, the description covers the essential matching logic and the safe preview workflow. Gaps around account selection (payment_account_id) and output format remain, but the core calling behavior is adequately conveyed.

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 56%, so some compensation is needed. The description explains dry_run and min_confidence behavior meaningfully and hints at the file-vs-linked-account choice, but says nothing about company_id, payment_account_id, mapping, from/to, or bank, leaving several parameters to the schema alone.

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 opens with a specific verb and resource ('Riconciliazione bancaria: abbina gli accrediti... alle fatture aperte') and enumerates the matching criteria (importo, numero fattura in causale, P.IVA, nome cliente). An agent can clearly distinguish this from siblings like mark_paid or bank_parse_statement.

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 spells out an explicit two-step workflow: dry_run defaults to TRUE for proposals, then re-run with dry_run=false to record matches ≥ min_confidence. It lacks explicit naming of alternatives (e.g., mark_paid) or exclusions, but the operational guidance is clear.

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