DiamondPaintingWinkel.nl shop advisor

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

Goes well beyond the readOnly/idempotent annotations: discloses that it performs GET requests to public shop prices and the download URL, that only the file header is read, and that the photo is never stored or uploaded and no order/payment is created. This is exactly the extra context annotations cannot carry.

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?

Front-loaded with purpose, then usage, then behavior and return values, and every sentence adds information. The trailing Dutch sentence largely duplicates the opening purpose statement, which is the one bit of waste.

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 fully covers what comes back (recommended size, alternatives, crop share, live price per size) and the side-effect profile. For a 5-parameter nested-input tool, 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 coverage is 100%, so the baseline is 3, but the description adds meaning: width/height are in pixels, the photo object is only header-read, and it clarifies that pixel dimensions and a photo/URL are interchangeable inputs. It does not mention wanted_size, so it stays just above baseline.

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: 'size and price advice for a custom diamond painting kit made from the customer's own photo'. It is clearly distinct from the siblings (search_products, shop_info), which deal with catalog and shop data rather than per-photo 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?

Gives concrete trigger questions ('whether their photo is suitable, which canvas size fits, or what a kit of their own photo costs') and boundaries ('measures resolution and aspect ratio only, not sharpness or lighting'). It does not explicitly name alternatives, but the siblings are unrelated enough that this is a minor gap.

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 readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, but the description adds meaningful context: reads the public catalogue via GET requests and does not create a cart, order or payment. Because there is no output schema, the note that results include current price, stock status and a product-page link is genuinely useful disclosure beyond the annotations.

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 contents, and read-only scope each earn their sentence. The closing Dutch sentence is a full restatement rather than new information, which is mild redundancy relative to a tight single-language description.

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 read-only, five-optional-parameter search tool with annotations covering the safety profile and no output schema, the description supplies what the agent needs: what is searched, when to use it, what the results contain, and what side effects do not occur. Nothing required for correct invocation 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 description coverage is 100%, so the schema already documents query, price bounds, sort enum and limit, including that an empty query returns the most popular products. The description only reinforces the subject-keyword idea and price-range filtering (and the Dutch line repeats 'onderwerp en budget'), adding no syntax or format detail beyond the schema. Baseline 3 applies.

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 a specific verb ("searches") and resource ("the live catalogue of DiamondPaintingWinkel.nl") with the exact object type (diamond painting kits), plus example subject terms and a price-range scope. It is unmistakably distinct from the siblings photo_size_advice and shop_info, which do not search products.

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 someone looks for a ready-made diamond painting kit or a gift" gives a clear triggering context, and "does not create a cart, order or payment" sets a firm out-of-scope boundary. It stops short of explicitly routing general shop questions to shop_info, but the positive/negative usage conditions are otherwise clear.

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 open-world, so the bar is lower. The description adds real value by disclosing the access mechanism (GET requests to public pages) and the fact that it never submits forms, contacts the shop, or modifies data, which goes beyond what the annotations state.

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 around purpose, scope and behavior with little waste. The trailing Dutch sentence largely restates the enum values already given in the schema, which is minor redundancy but not harmful.

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 usefully outlines what comes back (page text with a link, or an order-status link). Given a single-parameter, read-only tool, essentially everything needed to call it correctly 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 coverage is 100% and the sole 'topic' enum is already documented per-value in the schema. The description's list of topics mirrors that documentation rather than adding new format or precedence details, so it sits at the baseline.

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 (returns page text) plus the covered resources (levering, retour, FAQ, contact, bestelstatus) and explicitly contrasts with looking up individual orders. An agent can distinguish it from search_products and photo_size_advice 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' gives clear positive guidance, and 'Cannot look up or change individual orders' provides an explicit exclusion. It stops short of naming the sibling tools an agent should use instead for product search or photo sizing.

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