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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description reinforces that with 'it only sums what it is given,' confirming a side-effect-free, closed-world computation. It additionally discloses which formulas drive the output and that no tax determination occurs, adding real context beyond the annotations, though it says nothing about error behavior on unknown or missing box keys.

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 sentences, front-loaded with the action, then the accepted box list, then the example and the scope caveat. Every sentence carries information, though the inline enumeration of eight box numbers is slightly dense and could have been left to the schema.

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 single-parameter, no-output-schema computation tool with readOnlyHint annotations, the description covers purpose, input shape, the formulas applied, and the negative scope. The one gap is the return shape (which computed boxes the agent gets back), which the absence of an output schema leaves unstated.

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 100% and the nested casillas object already lists all accepted box numbers, so the baseline is 3; the description adds a concrete input example ({"09": 17430, "29": 9870}) and clarifies the values are cuotas per box. This meaningfully disambiguates the expected key format beyond the schema's terse 'Box number -> amount'.

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 precise verb (add up), the exact resource (the boxes/casillas of Spanish quarterly VAT return Modelo 303), and the rule set used (AEAT form formulas for boxes 27, 45, 46, 64, 66, 87, 69, 71). An agent can distinguish this pure-arithmetic tool from the unrelated sibling utilities (check_vat_number, validate_iban, get_obligation_dates) immediately.

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?

Explicitly delimits scope: 'it only sums what it is given: it does not decide which rate or deduction applies and it is not a tax return,' which tells the agent when this tool is and is not the right call. It does not, however, name any alternative tool or workflow for the cases it excludes, so it stops short of full routing guidance.

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