pp_search

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description layers substantial non-obvious behavior on top: the meaning of each `promotion_status` value, the fact that historical prices can be up to 60 days old and that the lowest row price may be one nobody is charging today, plus the caveat that Lidl and Vomar carry no rows under `private_label` rather than a guessed brand signal. This is real behavioral disclosure, not restatement.

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 front-loaded — purpose and browse semantics come first, then row interpretation, then slug/paging logistics. Each sentence carries actionable content (slug lists, status meanings, paging advice) and there is no filler or restatement of the name.

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 14-parameter, annotation-covered search with no output schema, the description does the heavy lifting on how to interpret a returned row and how to page. It stops short of describing the response shape or its fields beyond price and promotion_status, which is the one gap an agent composing a query could notice.

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%, so the schema already documents every parameter and the baseline would be 3. The description still adds meaning the schema lacks: the full ten-retailer slug list (the schema only shows four), the paging strategy, and the interpretation of `promotion_status` during price comparisons. It loses a point because the status values it describes (`active`, `upcoming`, `shelf`, `historical`) do not match the schema's enum (`active`, `upcoming`, `expired`), which could confuse a caller about valid filter inputs.

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 gives a specific verb and resource ('Search supermarket offers') and scopes it to the 10 named Dutch chains, so the agent immediately knows what the tool does. It does not, however, differentiate itself from overlapping siblings such as pp_get_promotional_products, pp_get_top_deals or pp_search_products_by_name, which an agent must infer from naming alone.

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?

Explicit when-to-use guidance is given for the main knobs: omit `q` or pass `*` to browse the whole catalogue, call `pp_get_categories` first because category slugs are not free text, and keep `page_size` modest and page through instead of asking for 100 rows. It also provides an explicit warning about filtering on `promotion_status` before quoting a best price, which is exactly the kind of conditional guidance that prevents wrong tool output.

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