Nummerschilderen.com shop advisor

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantive behavior beyond them: only the file header is read, the photo is never stored or viewed, public price and the supplied download URL are fetched via GET, and the analysis covers only resolution and aspect ratio — not sharpness or lighting. It also discloses what is returned (recommended size, alternatives, crop share, live price per size).

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 purpose, then usage, inputs, scope limits, and safety, in a logical order with no wasted clauses. The final Dutch sentence only restates the opening in another language, which is mild redundancy given the title is already Dutch.

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 5-parameter, nested-object tool with no output schema, the description covers inputs, the return payload, privacy/scope limits, and the network side effects an agent must anticipate. Nothing needed to call it correctly or set user expectations is missing.

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 baseline is 3; the description adds real meaning by explaining that width/height are pixels, that a user-supplied photo is read only at the header level, and that the URL is a GET-based alternative. It does not explain the wanted_size parameter's role beyond an implied 'which canvas size fits', so it falls short of full marks.

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 states a specific verb and resource: size and price advice for a custom paint-by-numbers kit made from the customer's own photo. It is immediately distinguishable from the siblings search_products and shop_info, which are generic shop tools rather than photo-based sizing advice.

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 explicit triggers — photo suitability, canvas size choice, and cost of a kit from one's own photo — plus explicit exclusions: it does not store or upload the photo and does not create an order or payment. Nothing about when to reach for this tool vs. others is left to inference.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them by specifying the access method ('reads the public catalogue via GET requests'), the explicit absence of side effects ('does not create a cart, order or payment'), and the live nature of the data. Return contents (price, stock status, product link) are also disclosed, which annotations alone cannot convey.

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 English portion is front-loaded and efficient: purpose, when-to-use, return values, then side-effect disclaimer. The trailing Dutch sentence is a near-verbatim translation that adds no new information and slightly pads the definition.

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?

With no output schema, the description correctly compensates by naming what comes back (current price, stock status, product link). Safety and side-effect expectations are covered and usage context is given. Minor gaps remain around result-count/pagination behavior and sorting, though the limit and sort parameters are documented in the schema.

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%, so every parameter is already documented with enums, bounds and defaults; the baseline is 3. The description reinforces the query parameter with illustrative subjects and mentions price range, but adds no syntax, format or edge-case detail beyond what the schema already supplies.

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?

States a specific verb and resource ('searches the live catalogue of Nummerschilderen.com for paint by numbers kits') plus the two facets it filters on (subject/keyword and price range). This clearly separates it from shop_info (shop metadata) and photo_size_advice (sizing help), so an agent can pick it without opening the 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?

Provides explicit usage context ('Use when someone looks for a ready-made paint by numbers kit or a gift'), which is a clear trigger. It does not, however, state when not to use it or name the sibling tools (shop_info, photo_size_advice) as alternatives, so the routing guidance is implicit rather than complete.

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

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld. The description adds genuinely new behavioral facts: it reads public information pages via GET requests, does not submit forms or contact the shop, and returns a page link or an order-status link. That is meaningful disclosure beyond the annotation set; only rate-limit or freshness/caching behavior is unstated.

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?

Scope and limitation are front-loaded in the first three sentences, and the negative constraints are grouped efficiently. The trailing Dutch sentence ('Levering, retour, veelgestelde vragen, contact en bestelstatus...') duplicates content already stated in English, costing some economy.

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 one-parameter read tool with no output schema, the description explains what is returned (page text plus link, or an order-status pointer) and what the tool will not do. The main gap is that it doesn't say how much text comes back or whether links are absolute, but the essential call context is present.

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% and the single enum parameter documents each value in Dutch. The description restates those topics in English and clarifies that 'bestelstatus' yields a status lookup rather than an order lookup, which is mildly additive but essentially duplicates the schema — baseline 3.

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?

States a specific verb and resource: returns the current text of Nummerschilderen.com's own pages on delivery, returns/cancellation, FAQ, contact, and order-status lookup. It also scopes what it is not ('cannot look up or change individual orders'), so an agent can distinguish it from product search or order-management tools without opening the 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?

'Use for questions about ordering from this shop' plus the explicit exclusion 'cannot look up or change individual orders' gives a clear use context and a clear boundary. It stops short of naming the sibling tools (search_products, photo_size_advice) as alternatives for those other needs, so it is strong but not fully explicit routing.

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