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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description meaningfully adds that results are computed server-side from live Fortnox data and aggregated across all pages, which tells the agent not to paginate. It says nothing about how missing or partially claimed deductions are reported, though the output schema likely carries that.

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: scope first, then usage, then data-source behaviour. The acronym expansion and example question both earn their place by disambiguating domain vocabulary. The trailing API documentation URL is the only element that could be trimmed without losing decision-relevant information.

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 zero-parameter, read-only diagnostic with an output schema and full annotation coverage, the description covers what the tool measures, when to reach for it, and where the data comes from. It stops short of describing how the two claim categories are presented or what an empty result means for the 'have we claimed everything' question, which is the one remaining ambiguity for this kind of audit tool.

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?

The tool takes zero parameters, so no parameter semantics are required; the baseline for a parameterless tool is 4. The description implicitly confirms that the check is global, with no company, period or customer filtering to supply.

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?

It uses a concrete verb (check/verify) against a precisely scoped resource, and it enumerates the two case categories it covers: paid-but-unsubmitted claims and claims awaiting a decision. It also expands the ROT/RUT acronym, so an agent unfamiliar with Swedish tax terminology can still tell what is being checked. The one gap is that it never distinguishes itself from the closely named sibling list_rot_rut_tax_reductions, so an agent must infer the boundary itself.

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?

'Use when the person asks whether all ROT and RUT has been claimed' gives a clear triggering condition, reinforced by a concrete Swedish-language example question. The guidance is clear context but offers no exclusions or named alternatives, so the agent is not told when a different tool would be the better choice.

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