DrMaker3D: custom 3D printing, figures, cookie cutters and gifts

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the content is a fixed catalogue of studio facts rather than live data, but says nothing about return format, freshness or size. With annotations carrying the behavioral load, a 3 is appropriate.

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 core purpose is front-loaded in the first clause, but the middle is a long comma-spliced enumeration of products ('figures ... pets, wedding cake toppers ... CookieMaker3D ... lake maps ... pendant lights') that reads as marketing copy. Much of it duplicates the enum values without adding selection-relevant detail, so the length is not fully earned.

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, yet the description makes clear what kind of prose content comes back and that it can answer 'what it makes, from what, how long it takes and how ordering works.' With a single optional enum parameter at 100% coverage, this is nearly complete; only the per-topic return contents are 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% and the single 'topic' parameter has a fully enumerated set with a description. The description's prose lists subject areas that map loosely onto the enum values (materials, ordering, lake maps, pendant lights, cookie cutters), but it never states what each topic value actually returns. Baseline 3 applies since the schema already does the documentation work.

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 states a specific resource and scope: an informational overview of the DrMaker3D studio (what it makes, materials, turnaround, ordering). The closing sentence makes the verb explicit ('Use it to answer questions about the studio'), so an agent knows this is a static content-retrieval tool. It does not explicitly name siblings, so it does not earn a 5.

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?

The final sentence gives clear usage context: answer questions about the studio's offerings, materials, timelines and ordering process. This implicitly routes transactional requests (quote_custom_print, create_checkout, track_order) elsewhere, but no exclusion is stated outright, so it stops short of a 5.

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?

Goes well beyond the annotations: nothing is charged, no order exists until payment, each print is re-priced server-side and request prices are ignored, and both returned links have distinct lifetimes (order_link 7 days, checkout_url 2 hours). This tells the agent exactly what mutation occurs and what to hand back to the person, which readOnlyHint=false/openWorldHint=true alone does not.

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-loads the core action and the no-charge guarantee, then handles parameters, then return values. It is dense and slightly long with one run-on enumeration of excluded product types, but every sentence carries operative 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?

With no output schema, the description fully carries the return contract (order_link vs checkout_url, their lifetimes, and which to give the person). Combined with the pricing and shipping caveats, an agent has everything needed to call this correctly and relay results.

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 baseline is 3, but the description adds real meaning: prints must be the checkout_item exactly as quote_custom_print returned it (prices ignored from the request), and the destination ZIP/postal code is required because shipping is priced to it. It does not explain agent, email, or the per-item finish/quality/infill fields, which remain schema-only.

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 (creates a Stripe Checkout link for custom prints) plus the exact precursor (quote_custom_print output). It also draws the boundary against the catalog/figures/keychains path, so the agent can distinguish it from siblings like search_products without inspecting schemas.

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?

Explicitly says when to use it (custom prints quoted with quote_custom_print, person pays in browser) and when not to (catalog products, figures, keychains, lithophanes, cake toppers, cookie cutters get their own pages from search_products or print_price_examples). The prerequisite chain to quote_custom_print is stated outright.

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, destructiveHint=false, and a closed world, so the safety profile is covered. The description adds behavioral value beyond that by framing this as a static reference catalogue and by stating a precondition relationship with quote_custom_print. Return format (text vs. structured table) is not described, which keeps it from a 5.

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?

Content is front-loaded with the enumerated reference data, and the second sentence carries the ordering rule without repetition. The first sentence is a long compound list that mixes 'accepted file formats' with 'how to upload a model file', which is slightly muddled but not padded.

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 parameters and no output schema, the description carries the burden of telling the agent what it will get back, and it does so by listing the domains of information returned. It stops short of describing the shape or volume of the response, but for a static reference tool this is close to sufficient.

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?

The tool takes zero parameters, so the baseline of 4 applies; there is nothing for the schema to document and nothing for the description to compensate for. The description correctly spends no words on arguments.

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 enumerates exactly what the tool returns: materials, colors (stock vs. special order), print qualities, infill, copy limits, max one-piece size, accepted file formats, and upload instructions. That is a concrete resource list an agent can act on, and it names quote_custom_print to separate it from the quoting tool. The only weakness is the absence of an explicit verb (e.g. 'Returns' or 'Lists'), so the action is implied rather than stated.

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 an unambiguous sequencing rule — 'Call it before quote_custom_print' — and explains why (so the material and color named are real ones). This ties usage directly to a named sibling, leaving nothing for the agent to infer about ordering.

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?

The annotations already establish that this is a safe, read-only, idempotent lookup. The description adds useful scope and caveats such as 'before shipping,' ranges for standing figures, fixed keychain pricing, and extra color costs, but it does not describe the return format or currency. With the safety profile already covered by annotations, this is adequate but not rich.

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 core purpose is front-loaded, and the usage boundary is clear. However, the final sentence is a dense run-on packed with product-variant details, making the description longer and harder to scan than necessary.

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 price-reference tool with one optional parameter and no output schema, the description explains what is covered and when exact pricing is required. It is nearly complete, though it omits currency and does not describe the returned price format.

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 schema fully documents the optional material parameter. The description only implies material filtering by saying prices are listed 'in each material,' so it adds little beyond the schema 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?

The description specifies a concrete verb and resource: it lists real reference prices from DrMaker3D's instant quote, including which parts and configurations are covered. It also distinguishes the tool from exact quoting by explaining that ballpark prices come from this tool while exact prices require file upload or a quote request.

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 usage guidance: use this to provide a ballpark, and use the instant quote page or quote request for exact pricing. The boundary between this reference-pricing tool and exact-quote workflows is 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?

Goes well beyond the annotations by disclosing a real side effect ('the file is kept privately by the studio'), the accepted formats and 25 MB cap, and the fallback behavior when a file can't be auto-quoted. The revelation that a file is retained is consistent with readOnlyHint=false rather than contradicting it.

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 the upload alternative, retention note, return values, and fallback in a logical order — every sentence carries information. It is dense, and the second sentence is a long run-on bundling endpoint, formats, size limit, and key prefix, which slightly hurts scannability.

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 10-parameter tool with a nested file object and no output schema, the description covers the essentials: which input form is required, what comes back (price, size, turnaround, checkout_item) and the handoff to create_checkout, plus what happens on unsupported files. An agent could invoke this correctly without further context.

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 already 100%, so the schema carries the per-parameter burden (color, units, infill, quality, material). The description still adds value the schema only hints at: the upload endpoint, the format/size constraints that govern 'file' vs 'file_key', and the meaning of the returned file_key prefix. It adds context but doesn't walk through the optional parameters.

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+resource ('exact instant-quote price for printing a person's 3D model file') and pins the source of truth ('same engine and same measurements as the instant quote page'). This clearly separates it from print_price_examples and request_quote, which are the nearest siblings.

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?

Explicitly names both input paths (pass the attached file, or upload first via POST /api/upload with kind=printiq and pass the returned key) and states exactly which cases this tool will NOT handle: painted multicolor, STEP, oversized-in-one-piece, and model links from Printables/Thingiverse/MakerWorld, routing those to request_quote. Nothing 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?

Beyond the annotations (openWorldHint=true, non-idempotent, non-destructive), it discloses the full downstream consequence: Rich replies by email within one business day with a price and payment link, the person pays in a browser, and nothing is charged here. For an outward-facing side-effecting tool this is exactly the context an agent needs to set expectations and avoid implying an in-tool purchase.

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?

Purpose and the permission constraint are front-loaded, and every sentence carries information (recipient, constraint, outcome, required inputs, file options). The final sentence is long and runs multiple clauses together, slightly hurting scannability.

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 9-parameter, non-idempotent, open-world submission tool with no output schema, the description covers prerequisites, expected inputs, accepted file forms, and the offline follow-up path. The only gap is that it never says what the tool itself returns to the agent (e.g., a confirmation or reference), which matters slightly given the absence of an output 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 coverage is already 89%, but the description adds real meaning beyond it: a file is optional, accepted formats are STL/OBJ/3MF/STEP or Printables/Thingiverse/MakerWorld links, and with no file the agent should supply measurements because design and printing are quoted together. That materially guides file_url, description, and wants beyond the schema definitions.

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 verb and resource ('Send a quote request ... for a person who wants something 3D printed or designed') and identifies the recipient and channel. An agent can immediately distinguish this from sibling tools like print_price_examples or search_products, though explicit routing against quote_custom_print is left to the file_key parameter text.

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 a hard prerequisite ('Only with the person's permission, and only with their own name and email') and tells the agent what information to gather (what it is, size, material/color, quantity, deadline). What's missing is explicit guidance on when to pick this versus quote_custom_print or create_checkout, so there is context but no alternatives or exclusions.

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, and closed-world scope, so the safety profile is covered. The description adds real context beyond them: the return payload shape (titles, starting prices in USD, links) and the qualifier 'where there is one', warning that some results carry no price. It doesn't cover result ordering or relevance behavior.

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 the verb and scope, then the fallback routing — good ordering with no wasted framing. The long parenthetical catalogues of product and service types are slightly heavy but do real work for query formulation and coverage signalling.

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 only two optional parameters, no output schema and full annotation coverage, the description supplies everything an agent needs: what is searchable, what comes back, how to fall back for custom prints, and that an empty query lists the shop. No material gap remains.

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 both parameters are documented there, including the empty-query-lists-shop behavior, so the baseline is 3. The description only restates that matching is 'by words' and never mentions the limit parameter or any matching nuance (substring, multi-word, ranking) that would add value over the schema.

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 (search the DrMaker3D shop and its service pages) and enumerates the content domain so an agent knows exactly what corpus is indexed. It also distinguishes itself from three siblings (about_drmaker3d, print_price_examples, request_quote) for the custom-print case, and names what it returns (titles, starting prices, links).

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 a clear trigger (match by words) plus an explicit exclusion with named alternatives: a custom print from a file has no product, so route to about_drmaker3d, print_price_examples or request_quote. It stops short of a full routing table — sibling print_options is never mentioned, and no guidance is given on choosing between searching and browsing.

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 cover read-only, idempotent, closed-world and non-destructive, so the safety profile is settled. The description adds meaningful behavioral context beyond that: the two-parameter pair functions as an authorization check (order number + checkout email), and the 'only that order is ever returned' line tells the agent no other orders leak into the response — important for a lookup keyed on customer identity.

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?

One dense sentence plus a short constraint clause — nothing wasted, and the return contents are front-loaded before the requirements. The opening is grammatically incomplete ('The stage of a DrMaker3D order...' with no verb), which costs a small amount of clarity, but the information density is high.

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 carries the burden of describing the response — and it does, listing stage, ship-by date, arrival window, and tracking-when-shipped. Combined with annotations covering the safety profile and 100% parameter documentation, an agent has everything needed to call this correctly; only response shape details (types, date formats) are absent.

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% with both parameters documented (email = used at checkout, order_number = e.g. DM1015), so the schema does the heavy lifting. The description largely restates those two fields, adding only the example format inline. Baseline 3 is appropriate when structured data already documents every parameter.

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 exact resource (a DrMaker3D order) and enumerates what the caller learns: stage values (received, printing, finishing, shipped, delivered), ship-by day, arrival window, and tracking number. The opening is an elliptical noun phrase rather than a verb, so it leans on the title for the action, but the content is specific enough that an agent immediately knows what comes back.

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 prerequisites plainly (order number like DM1015 plus the checkout email) and constrains the result: 'only that order is ever returned.' No sibling tool overlaps with order tracking, so no exclusions are needed. It stops short of explicitly saying 'use this when a customer asks about order status,' but that context is obvious from the resource.

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