tax_estimate

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

Annotations only declare readOnlyHint, and the description adds substantive behavior: it depends on state previously written by tax_profile_set, consumes recorded receipts, and enumerates the computed figures returned rather than just saying 'estimates tax'. It does not discuss assumptions, rounding, or what happens when no tax profile exists.

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?

Three dense sentences, front-loaded with the purpose and the two payment dates, then data sources, then parameter guidance. No filler, though the middle sentence could be read as a run-on and the ordering of sources before parameter guidance is slightly awkward.

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 read-only four-parameter tool with no output schema, the description covers the source data, the projection choice, and the return figures, which is nearly everything an agent needs. It stops short of describing output shape or edge cases such as a missing or incomplete tax profile.

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 75%, and the one gap is projection, whose enum values the description explains in concrete terms ('project current-year revenue to year end' vs 'only what has already occurred'). It also implicitly frames revenue_estimate as an override for the projection, adding meaning beyond the schema's own wording.

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 gives a specific verb and resource ('Stima imposta sostitutiva e contributi del forfettario') plus the exact outputs (30 June saldo + 1° acconto, 30 November 2° acconto, annual total, percentage to set aside). It is clearly distinct from CRUD siblings and from tax_profile_set, though it never names the closest sibling regime_simulator, leaving slight overlap ambiguity.

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 where the numbers come from (receipts in Fatture in Cloud, profile from tax_profile_set) and gives explicit conditional guidance for the projection parameter: 'linear' to project current-year revenue to year end, 'to_date' to use only revenue already recorded. What is missing is any exclusion or named alternative (e.g. when to prefer regime_simulator).

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