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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: provenance ('as read from the stores' own sites'), the fact that 'aangekondigd' campaigns are announced but not yet running, and that each result nests the underlying dealio promotions with their links. It stops short of saying anything about freshness/caching or result ordering.

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 resource and its data source are front-loaded, which is good, but the description is a single ~90-word run-on that re-lists every campaign kind ('1+1, 2e halve prijs', 'no VAT', 'loyalty-card deals') already enumerated in the kind schema. That list is dead weight; trimming it would sharpen the definition without losing 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?

There is no output schema, and the description compensates fully by enumerating the returned fields (store, kind, advantage, applies-to, condition, code, validity, product vs. basket, link, nested promotions). Combined with a complete input schema and read-only annotations, an agent has everything needed to call it 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 description coverage is 100%, including per-enum-value explanations, so the schema already carries the parameter meaning. The description's 'Filter by store, kind or words' and 'whether it works on products or on the whole basket' merely restate the q/store/kind/reach fields and duplicate the kind vocabulary verbatim from the enum.

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 first sentence names a specific resource (store campaigns / winkelacties at Belgian retailers) and its source (the stores' own sites via dealio.be/acties/). It then explicitly excludes the nearest sibling: 'Not one product's price (that is search_deals).' An agent can distinguish this from search_deals without opening either schema.

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 the exclusion against search_deals and tells the agent it can 'Filter by store, kind or words', with the store filter pointing to list_stores in the schema. It doesn't cover when to prefer get_deal for a single promotion even though it mentions nested promotions 'on dealio that fall under it', so routing is clear but not exhaustive.

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