Make Parts Now: 3D Printing & CNC Machining Quotes

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

Annotations declare the safety profile (readOnly=false, idempotent=false, openWorld=true), but the description adds two things annotations cannot: that accept_terms must be true or the call fails, and that the api_key is shown only once (non-recoverable). That is meaningful behavioral context beyond the structured fields.

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?

Three short sentences, front-loaded with the core action and the hard gating requirement, then the address shape and the one-time key. Efficient, though the ship_to restatement duplicates the schema rather than earning its place.

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?

An output schema exists so return values need not be explained, and the description covers the critical validation and one-time-secret behavior. It omits prerequisites (no existing account required?), webhook/callback expectations, and how to recover or rotate the key, which would fully round it out.

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 description's parameter text (accept_terms requirement, ship_to object shape) is verbatim-equivalent to the schema descriptions. It adds no syntax, constraint, or default information the schema lacks, so the 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?

States a specific verb and resource ('Create an autonomous agent account and API key'), which clearly separates it from read-oriented siblings like get_account and from order-flow tools like create_checkout_link. It does not explicitly name or contrast with any sibling, so it stops short of 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?

Usage is only implied: the tool is evidently the onboarding step that must precede order/quote tools, but the description never says when to call it versus get_account or what the prerequisite state is. No exclusions or alternatives are given.

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 flag destructiveHint=true and idempotentHint=false; the description explains the mechanism behind that destructiveness by stating each new link invalidates earlier links for the same quote, plus that tax is added at checkout. It omits auth/side-effect details but adds genuine behavioral value beyond the structured flags.

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?

Two short sentences, front-loaded with the core action and followed by the key side effect. No padding or repetition of schema content.

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?

An output schema exists, so return-value detail is unnecessary, and the description covers the operation and its invalidation side effect. The main gap is not naming the alternative payment tool, which matters for agent routing.

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 quote_id parameter is documented as originating from create_quote (qt_...). The description adds nothing about the parameter, so the baseline 3 for fully covered schema is appropriate.

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: obtaining a Stripe Checkout URL for card payment, scoped to a quote. The 'Option A' framing signals an alternative payment path exists, but does not name it (the sibling pay_with_crypto), so sibling differentiation is implied rather than explicit.

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?

'for a human to pay by card' scopes the audience and payment method, implying when this applies. However, it never states when to prefer this over the crypto alternative or any prerequisites, leaving routing to inference from the bare 'Option A' label.

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 this a non-readonly, non-idempotent, non-destructive, closed-world mutation, so the safety profile is provided structurally. The description adds the useful fact that a successful call returns prices, speed options with ship/arrival dates, and next_steps, but says nothing about auth requirements, whether quoted prices are locked, or side effects of creation.

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?

Three short, front-loaded lines with no filler; the core action comes first, then the payload, then the pointer. The telegraphic style is slightly dense but every sentence carries 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?

For a 5-param mutation with full schema coverage and an output schema, the description is largely sufficient: it names the required items payload, the id source, and the return shape. The remaining gap is workflow context — nothing says what to do with the returned next_steps or how quote creation relates to checkout/payment siblings.

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 every parameter (speed enum values, ship_to address fields, po_number, contact_email). The description restates the items/config shape and points to get_capabilities for ids, which is mildly helpful but adds little 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?

States a specific verb and resource ('Create a quote') and even sketches the payload shape via the items array, so an agent knows exactly what this does. It does not, however, distinguish itself from siblings like update_quote or get_quote, so it stops short of 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 only routing hint is 'See get_capabilities for valid ids,' which is really a pointer for populating parameters rather than guidance on when to call this tool. There is no statement of when to use create_quote versus update_quote/get_quote, nor any prerequisite or exclusion context.

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 destructiveHint=false, so safety is covered. The description adds that it returns the authenticated account specifically (not an arbitrary account) and lists fields, but those fields are likely also in the output schema, so the added value is modest.

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 a single, short fragment that front-loads the resource and its contents. Every word contributes, and there is no unnecessary verbosity.

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?

Given the simplicity (no parameters), read-only annotations, and an existing output schema, the description is nearly complete. The only minor gap is the absence of an explicit verb, but the fragment 'The authenticated account: ...' is sufficient for an agent to understand the tool's purpose.

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?

There are zero parameters, so the baseline is 4. The description does not need to explain parameter semantics, and it provides no misleading parameter information.

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 identifies the resource (the authenticated account) and enumerates the fields returned, so an agent can tell what it provides. However, it lacks an explicit action verb and does not differentiate from sibling tools such as get_capabilities or get_order, so it falls short of 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives are provided. The description only states what the tool returns, leaving an agent to infer the appropriate context.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds a content list but no behavioral context such as caching, authentication requirements, or how the data is sourced, so it adds little beyond structured fields.

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 a single concise fragment, front-loaded with the capability categories. Every word contributes to defining the scope, with no wasted text. It is a list rather than a sentence, but that is appropriate for a zero-parameter getter.

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 an output schema and rich annotations, the description only needs to cover purpose and usage. It covers purpose via the category list but omits any usage guidance or differentiation. For a simple zero-parameter tool, this is minimally viable, but the missing when-to-use context is a clear gap.

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 is 4 per the rules. The description does not need to explain parameter semantics, and none are present to document.

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 the specific capability categories returned (processes, materials, colors, finishes, services, speeds, file formats, limits, payment methods), making the resource scope very clear. It lacks an action verb (relying on the tool name) and does not differentiate from siblings, but no sibling overlaps in purpose.

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?

No when-to-use guidance is provided, no alternatives mentioned, and no prerequisites stated. The description only lists content, leaving the agent to infer when this tool should be called.

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 openWorldHint=false, so the safety profile is fully covered. The description adds no behavioral context beyond the field list — no error behavior for unknown order ids, no permission or rate-limit notes — so it contributes little on this dimension.

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?

It is a single terse fragment with no filler, and the most useful content leads. But it is a verbless noun phrase rather than a structured statement, which reads as under-specification rather than disciplined brevity.

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?

An output schema exists, so the returned fields (status, dates, tracking) did not need restating here, and annotations cover the safety profile. The genuine gaps — how it differs from list_orders/get_quote and behavior on a missing order — are minor for such a simple one-parameter read tool.

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?

There is a single parameter with 100% schema description coverage, and the schema description is richer than the tool description, naming the ord_... prefix and the sources (list_orders, paid quote). Baseline 3 applies since the schema does all the 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 fragment names the resource (order) and enumerates the data it surfaces (status, ship-by/arrive-by dates, tracking), so an agent can infer this is a single-order lookup. However, it supplies no verb and gives no signal distinguishing it from list_orders or get_quote, so the purpose is only implied.

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 description says nothing about when to call this tool versus list_orders (bulk) or get_quote (pre-purchase). The only routing hint, 'from list_orders or the paid quote', lives in the input schema, not the description.

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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety and repeatability profile is fully covered. The description adds only that measurements are in millimeters and that DFM warnings/process fits are included, which is modest added context. It says nothing about error behavior for an unknown or stale part_id.

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 tight, front-loaded sentence with no filler; every listed item is substantive. It loses a point only because the fragment form omits the verb, making the sentence slightly less self-contained than it could be at the same length.

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 simple one-parameter read tool, the structured fields carry most of the load: annotations cover the safety profile, the schema documents the ID, and an output schema exists so return values need not be restated. The description is therefore largely sufficient, with the only real gap being the absent statement of when this tool should be chosen over its upload/URL siblings.

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?

There is a single parameter with 100% schema description coverage, and the schema already explains that part_id is a 'prt_...' value returned by upload_part or get_upload_url. The description contributes no additional parameter meaning, so the baseline of 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 enumerates the returned payload (status, geometry in mm, suggested units, DFM warnings, fit processes) but never states the action or that it is a lookup by part_id. The resource ('part') is identifiable from the name, yet the description alone reads as a field list rather than a verb+resource statement, and it makes no attempt to distinguish itself from siblings like upload_part, get_upload_url, or get_order.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternative tools. An agent must infer from the name and the schema's part_id note (that IDs come from upload_part or get_upload_url) that this is the follow-up read after an upload, which is the kind of routing the description should state explicitly.

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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds that the response carries 'warnings' and 'next_steps', a useful behavioral hint about output content, but says nothing about freshness/expiry of the quote or error behavior for an unknown id.

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 compact sentence with no filler, and the most decision-relevant element (current pricing) is front-loaded. The trailing list of output categories is slightly enumerative but still earns its space.

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 an output schema present, the description needn't explain return values, and it correctly does not attempt to. Combined with annotations covering the read-only profile and a single well-documented required param, this is nearly sufficient; only usage routing to siblings 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% and the single quote_id parameter is already documented as a 'qt_...' id from create_quote, so the description contributes nothing parameter-specific. Baseline 3 applies when the schema carries the full burden.

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 resource (a quote) and enumerates the data it surfaces — pricing, speeds, shipping options, warnings, next_steps — which is more concrete than the bare name. However it never states the verb explicitly (retrieve/fetch a quote by id) and does nothing to distinguish it from siblings like get_order or get_quote-adjacent tools, so an agent must infer the retrieval semantics.

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?

There is no statement of when to call this versus create_quote, update_quote, or get_order, and no prerequisites. The only usage hint is indirect, coming from the schema's note that quote_id is 'returned by create_quote', which is not in the description itself.

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 only declare the non-read-only, non-idempotent, non-destructive profile; the description adds genuinely new context: the URL is one-time, requires no auth header, and the part is returned on upload. It does not state how long the URL stays valid or what happens if the PUT fails.

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?

Two short sentences, front-loaded with the core action and the key operational detail (no auth header), with zero filler.

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 an output schema present, return values need no explanation, and the description covers the auth exception. However, for a workflow tool that sits alongside upload_part, omitting how the two relate and how long the one-time URL lives leaves a meaningful gap for correct invocation sequencing.

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 already documented in the schema (including the allowed file extensions and the CUI/ITAR confirmation). The description adds no parameter-level meaning beyond that, so the baseline of 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?

States a specific verb+resource (get a one-time URL) and the intended mechanism (HTTP PUT directly, no auth header). It is clear what the tool produces, but it never distinguishes itself from the sibling upload_part, which an agent could easily confuse with this pre-upload step.

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?

'large file' implies a size-based usage condition versus presumably smaller uploads, but there is no explicit when-to-use/when-not or any pointer to upload_part as the alternative path. Usage must be inferred rather than read.

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, and non-destructive, so safety is covered. The description adds context annotations do not carry: results are scoped to 'this account' and sorted newest-first, which tells the agent what to expect from the result set.

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?

Two short sentences, the default ordering is front-loaded, and the filter guidance follows immediately. No sentence is wasted.

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 an output schema present, return formatting is covered, and annotations cover the safety profile. For a one-optional-param list tool this is nearly complete; the only omission is any mention of result limits or pagination behavior.

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 already documents quote_id's format (qt_...), so the baseline is 3. The description goes beyond that by explaining the intent behind the filter (verifying a checkout link was paid), which is meaning the schema does not supply.

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 resource ('Orders for this account') and a default ordering ('newest first'), which is enough to distinguish it from the singular get_order sibling. It stops short of using an explicit listing verb, but the resource+scope pairing is clear.

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 one concrete use case ('filter by quote_id to check whether a checkout link was paid'), which implies when to reach for the filter. It never states when not to use this tool or points to alternatives like get_order for a single order, leaving routing 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 flag destructive, non-idempotent, open-world behavior; the description adds the two-phase handshake and the agent-account restriction, which are real behavioral facts. It stays silent on funding/credit interaction and failure handling, but adds clear value 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?

Three short lines, front-loaded with the action and the constraint, then the mechanics. No filler; every sentence earns its place.

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?

Output schema exists so return values need not be described, and the agent-only scope plus the two-step flow cover the essentials. Minor gaps remain around credit application and what happens if signing fails.

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 explains the round-trip semantics of payment_signature (first call omits it, second call carries the base64 PAYMENT-SIGNATURE) in a way the schema field text only partially captures.

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+mechanism: 'pay autonomously in USDC via x402', and scopes the audience with 'agent accounts only', which separates it from sibling checkout/quote tools.

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 call sequencing: omit payment_signature to fetch requirements, then sign and call again. It does not, however, say when to prefer this over sibling paths like create_checkout_link or credit-only payment, so the routing guidance is incomplete.

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=false, idempotentHint=true, and destructiveHint=false, so the safety and repeatability profile is covered. The description adds genuine behavioral meaning by explaining where each refund route lands (paying wallet vs account credit), but says nothing about reversibility, timing relative to a refund event, or whether it is per-order or account-wide.

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?

A single sentence with the scope condition front-loaded and zero filler. It earns its place, though the value definitions duplicate what the enum descriptions already carry, so it is slightly redundant rather than maximally tight.

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 an output schema present, return values need no explanation, and annotations plus full schema coverage carry the mechanics. What is still missing for a mutation tool is lifecycle context: whether the preference must be set before a refund is triggered and whether it can be overwritten later.

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 schema already documents both the enum meanings and the order_id format. The description's parentheticals restate the same enum semantics rather than adding format, constraints, or defaults, so it is a 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?

The description names the specific setting (refund preference), its applicable scope (USDC orders), and enumerates the two behaviors. An agent can tell this apart from every sibling, none of which touch refunds. It stops short of a clean verb+resource phrasing like 'Sets the refund preference for an order', but the intent is unambiguous.

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 qualifier 'For USDC orders' acts as an implicit precondition, telling the agent this tool is only relevant to USDC-paid orders. However, it gives no guidance on when to call it relative to the payment/refund lifecycle, whether it can be changed after being set, or what alternatives exist for non-USDC orders.

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 destructiveHint=true and idempotentHint=false, so safety is covered by structured data. The only behavioral note ('config is merged into the item's config') is verbatim from the schema's update_items description, so the description adds no value beyond what annotations and schema already provide.

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?

Two short, front-loaded sentences with no filler; the mutable fields are listed immediately. It is terse to the point of being cryptic, but nothing is wasted.

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?

An output schema exists and schema coverage is 100%, so return values and parameter shapes are covered. For a destructive 9-parameter mutation, the description still omits editability preconditions and the consequence of overwriting existing quote data, leaving it only minimally 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?

Schema description coverage is 100% and every parameter is documented there, so the baseline is 3. The description echoes the speed enum and the update_items shape but adds no syntax, constraints, or semantics beyond 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 clear verb (Change) and enumerates the mutable resources (speed, ship_to, shipping_option, items). It is distinguishable from create_quote by the mutation framing, though it never explicitly names the sibling it complements.

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?

No when-to-use guidance, no prerequisites (e.g. quote must exist and be in an editable state), and no mention of alternatives like create_quote or get_quote. The agent must infer that this modifies an existing quote from the name alone.

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 only declare it is a non-read-only, non-idempotent, open-world write; the description goes well beyond by disclosing the 4 MB transport ceiling, the ~3 MB base64 practical limit, the mandatory no_controlled_data compliance gate (CUI/ITAR/export-controlled), and the asynchronous lifecycle (returns status 'pending', poll get_part until 'ready'). It does not contradict any annotation.

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?

Four sentences, front-loaded with the capability and formats, then limits, then the compliance prerequisite, then the async follow-up. Every sentence carries a distinct, load-bearing fact; nothing is padded or restated.

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?

Output schema exists so return values need not be spelled out, yet the description still flags the 'pending' status and the polling step, which is the piece an agent actually needs to act on. Combined with the size limits and the compliance gate, nothing required to invoke this correctly 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 baseline is 3, but the description adds real meaning on top: it explains that filename is required when using base64 and that no_controlled_data is a compliance assertion about export-controlled data rather than a mere flag. It does not add format or syntax detail for the url field itself.

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?

Specific verb ('Upload') plus resource ('a CAD file') with the accepted formats enumerated (STL, 3MF, OBJ, STEP) and the two input channels named. An agent can distinguish this immediately from siblings like get_part, get_upload_url, or create_quote without opening any 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?

Explicitly states the decision rule between the two modes: base64 works for files up to about 3 MB due to the 4 MB MCP request cap, while 'use a URL or get_upload_url for larger files' names the alternative sibling and the condition that selects it. It also states the filename-required-for-base64 precondition.

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