list_deductions

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

With no annotations provided, the description carries the full disclosure burden. It discloses that the tool returns default values, marks editable lines, and notes that non-editable lines are computed by the model. It also reveals the integration point with calculate_tax. It does not explicitly state whether the call is read-only, but 'Show' strongly implies a non-mutating operation.

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 description is front-loaded with the core purpose and then adds only essential detail: what line items are returned, which are editable, how overrides work, and which lines are model-computed. Every sentence earns its place; there is no filler or redundancy.

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?

The description explains the output semantics and the connection to calculate_tax well, and an output schema exists to cover return structure. However, with 14 parameters, no annotations, and only 29% schema description coverage, the input side is under-served. The agent can infer some meaning from parameter names and defaults, but the description does not explain how household characteristics map to the deduction sheet.

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 only 29%, so the description needed to compensate by explaining how parameters like location, income1, tax_year, relationship, and others affect the output. It does not; it focuses entirely on the output shape and the link to calculate_tax. The example deduction ids (PRAEMIEN3A, SCHULDZINSEN) relate to the output, not to the input parameters.

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: 'Show the deduction/budget sheet ESTV derives for a household.' It then clarifies the exact scope by saying it returns every line item with default values and distinguishes editable from non-editable lines. This clearly differentiates it from calculate_tax and other siblings.

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?

The description explains how the tool relates to calculate_tax: editable lines can be overridden through the `deductions` argument of calculate_tax, keyed by id. This implies the intended workflow of inspecting defaults before overriding them, though it does not explicitly state 'use this when...' or list exclusions.

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