koebsmoenster

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description adds value on top by disclosing the data source (saved receipts, currently Coop/Brugsen) and the coverage caveat that receipts cover only part of total purchases. It does not state how far back receipts go or what happens when no receipts exist, which a read-only analytics tool would ideally mention.

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 definition is dense but front-loaded: it leads with what the household actually buys and the source, then lists returned fields, then use cases. Every clause carries information; the only mild cost is that field-level detail and usage guidance are interleaved rather than separated.

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?

There is no output schema, so the description must describe return values itself, and it does so field by field (basisvarer, interval, dage siden sidst, favoritter, øko-andel, forbrug pr. uge, andel_af_indkoeb). Combined with the readOnly annotation and the coverage caveat, an agent has enough to call it and interpret the result correctly.

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 0% and the single parameter has only a default of 1, so the description carries the burden — and it does explain that `andel_af_indkoeb` is the share of purchases the receipts cover (e.g. 0.7 per the profile note), enabling budget extrapolation. What remains unclear is whether passing a different value changes the returned figures or is purely informational.

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 names the resource and its scope precisely: household purchase patterns derived from stored receipts (currently Coop/Brugsen), and enumerates the returned dimensions (basisvarer with intervals, favorites per category, spend breakdown, organic share, weekly consumption). It is clearly distinct from siblings like vis_beholdning or tidligere_ordrer by virtue of being a derived analytics view, though it never names a sibling explicitly.

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 gives three concrete use cases: meal planning from liked dishes, suggesting staples that are running low (snart_tom), and comparing the weekly budget against actual spend. That is clear when-to-use context, but there are no exclusions or named alternatives, so an agent must infer that inventory/order tools serve different needs.

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