Jurk Shenzhen Electronic Component Sourcing

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

Annotations already declare a non-read-only, open-world, non-idempotent, non-destructive operation. The description adds a genuine boundary disclosure not present in the annotations: 'No purchase or shipment is automatically authorized by calling this tool,' which tells the agent the call has a softer side-effect profile than 'request' might imply.

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 scope; the authorization caveat is appropriately placed last. No 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?

An output schema exists so return values need not be explained, but with 6 undocumented parameters and a confirm_submission flag implying a two-step confirmation flow, the description leaves an agent without enough information to invoke this 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 description coverage is 0% across 6 parameters, so the description carries the full burden. It gestures at 'pickup/delivery parties and instructions' (loosely mapping to contact/task) but says nothing about subject, language, location, or the critical confirm_submission flag that gates actual submission.

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 ('collect or deliver a sample') with a clear geographic scope ('in Shenzhen'). It is distinguishable from most siblings, though it does not explicitly contrast itself with the closely related 'shenzhen_errand'.

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 implied usage guidance by telling the caller to 'include pickup/delivery parties and instructions', but never says when to prefer this over alternatives such as shenzhen_errand, nor what prerequisites exist.

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 readOnlyHint=false, openWorldHint=true and idempotentHint=false. The description usefully adds that a human operator in Shenzhen performs the work, which is real-world context annotations cannot express, but it says nothing about turnaround, cost, how submission is confirmed, or what happens after the request is filed.

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 purpose before the input instruction. The only blemish is the ambiguous 'subject/task' phrasing, which forces the agent to guess which field receives the image reference.

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 described, and the core intent is conveyed. However, for an open-world request that dispatches a human, omitting any mention of the required contact field and the confirm_submission gate leaves the agent under-equipped to invoke 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 description coverage is 0%, so the description must carry all five parameters, yet it only touches task/subject and merges them ambiguously ('Put the accessible image URL/reference and identifying details in subject/task'). The required 'contact' parameter, 'language', and especially the 'confirm_submission' flag go entirely unexplained.

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?

Names a specific verb (request human help to identify/find) plus a concrete resource (item from a photo, visual reference or description) scoped to Shenzhen. It stands apart from delivery/logistics siblings like collect_or_deliver_sample or shenzhen_errand, though it never names the nearest alternatives (request_huaqiangbei_search).

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?

Implies the use case ('from a photo, visual reference or description') and tells the caller where to put the image URL, but gives no when-to-use-vs-alternative guidance. Nothing says whether this is for identification only, physical retrieval, or both, though both are listed.

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 'Read-only' in the description is a restatement rather than new information. The only added context is that the contact is 'public' and that request channels are returned, which is modest value on top of the annotation 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, front-loaded with the purpose and followed by the safety profile. Nothing is wasted or buried.

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 return shape need not be described, and the annotations fully cover the safety profile. The remaining gap is the absence of routing guidance among the many contact/capability 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?

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter semantics for the description to explain.

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: return the public Jurk sourcing contact plus available request channels. This is distinguishable from the near-neighbor get_shenzhen_execution_contact by naming the Jurk sourcing context, though it does not explicitly contrast with that sibling.

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 the many sibling contact/capability tools, and no prerequisites or exclusions. 'Read-only' is a property, not usage guidance.

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 and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: results are public, and the tool will never fabricate customer cases, which is a meaningful trust guarantee for an agent deciding whether to cite the output.

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 sentences with the core purpose first and no padding. The trailing 'Read-only.' sentence is largely redundant with the readOnlyHint annotation, which is a minor waste of the limited 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 need not explain return values, and with zero parameters there is no argument surface to document. It covers the availability caveat and the anti-fabrication guarantee, leaving only minor gaps such as result ordering or recency window definition.

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 per the rubric the baseline is 4. The description correctly implies a no-argument, no-filter retrieval, and there are no parameter semantics left for it to compensate for.

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 gives a specific verb ('Return') and resource ('public recent sourcing cases') with a scoping qualifier ('when verified case data is available'). It is clearly distinguishable from siblings like get_contact or get_service_area, though it does not explicitly name what makes it different from the capability-listing 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?

The phrase 'when verified case data is available' implies a usage condition, but it is a caveat about data availability rather than guidance on when an agent should choose this tool over siblings. No alternatives or exclusions are named, so usage remains inferred.

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 connection already declares readOnlyHint, idempotentHint, and destructiveHint=false, so the trailing 'Read-only.' adds almost nothing. What the description does contribute is the scope of the payload (both physical area and remote-request availability), which is more than the bare name conveys, but it says nothing about auth requirements or what a missing/unsupported area looks like.

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 return payload; nothing is verbose or buried. The only near-wasted clause is 'Read-only.', which duplicates the annotations, and 'for Jurk sourcing and supplier verification' is somewhat circular.

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 need not explain return structure, and with zero parameters the input side is trivially complete. The remaining gap is scope: what 'service area' and 'remote-request availability' actually mean and whether the result can be empty for unsupported regions.

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 there is no parameter semantics to get wrong — baseline 4 applies. The description correctly implies the input is the ambient account/session context rather than any argument.

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 ('Return') and a specific resource ('the physical service area and remote-request availability'), tied to a named domain (Jurk sourcing and supplier verification). It is clearly distinct in subject matter from capability-oriented siblings like get_sourcing_capabilities, though it does not explicitly contrast itself with any of them.

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 context is only implied by the phrase 'for Jurk sourcing and supplier verification' — an agent can infer this is a prerequisite-style lookup, but there is no explicit when-to-use, when-not-to-use, or named alternative among the sibling tools.

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=false and destructiveHint=false, so the safety profile is fully covered by structured data. The description's 'Read-only' merely restates the annotation and adds no new behavioral context such as freshness of capability data or rate limits.

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, purpose front-loaded, zero filler. Every clause carries information about what is returned and when to call it.

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 no-argument read tool with an output schema, the description need not explain return values, and the purpose plus usage trigger are covered. It stops short of identifying which sibling to use instead for adjacent ground-execution tasks.

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; there are no parameter semantics for the description to clarify, and the schema needs no compensation.

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 (return) and resource (Shenzhen physical human-execution capabilities) owned by Vladimir, which an agent can distinguish from get_sourcing_capabilities or get_supplier_check_capabilities. It does not explicitly contrast with those siblings, so a 5 is not warranted.

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 this to discover tasks that require a person on the ground' gives a clear trigger condition, but names no alternatives or exclusions — e.g., get_shenzhen_execution_contact or shenzhen_errand, which sound adjacent. Usage is implied rather than routed.

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, and destructiveHint=false, so the trailing 'Read-only.' is pure duplication. The only genuinely new signal is the word 'public,' hinting the returned identity is non-sensitive, but nothing is said about auth requirements, caching, or data freshness.

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 resource being fetched. The second sentence ('Read-only.') is redundant with the annotations and does not earn its place, keeping this just short of a 5.

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 a zero-parameter getter is simple enough that the description is nearly sufficient. The unexplained jargon ('Vladimir's Shenzhen Human Execution') and lack of sibling differentiation are the only remaining gaps.

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 rubric; there is nothing for the description to disambiguate. Schema description coverage is also 100%.

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 gives a concrete verb ('Return') and a specific resource ('public service identity for Vladimir's Shenzhen Human Execution and supplier-verification branch'), so the agent knows this is a getter for a branch-specific contact. It does not, however, distinguish itself from the generic 'get_contact' sibling, leaving the reader to guess which one to pick.

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 use this tool versus get_contact, get_shenzhen_execution_capabilities, or the other branch tools. 'Read-only' describes behavior, not usage context, so the agent gets no routing guidance.

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, and the description's 'Read-only' merely restates them. It adds no behavioral context such as freshness of the capability data, sourcing lead times or scope limits beyond the category list.

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 front-loaded sentence followed by a two-word safety tag; every element is load-bearing and nothing is 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?

For a no-parameter, read-only informational tool with an output schema, the description states exactly what content will be returned and the annotations cover the safety profile. Nothing an agent needs in order to invoke it correctly is 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?

The tool takes zero parameters, so the schema carries no parameter semantics to supplement; baseline is 4. Nothing in the description is needed or missing on this dimension.

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 ('Describe') plus a precisely scoped resource: Jurk's human component sourcing capabilities in Shenzhen, broken down into BOM, hard-to-find, obsolete, EOL and spot-market sourcing. The content scope implicitly separates it from get_supplier_check_capabilities, but the description never names or contrasts that sibling, so it stops short of explicit differentiation.

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 or when-not-to-use guidance is given, and no alternatives are named. With a sibling like get_supplier_check_capabilities covering adjacent 'capabilities' territory, the agent receives no explicit cue for choosing between them.

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 the trailing 'Read-only' is largely redundant. The description does add real scope context (independent checking plus optional physical on-site verification, Shenzhen-specific), which is useful beyond the annotations but still thin.

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 compact sentence, well front-loaded with the core action and scope. The appended 'Read-only' is redundant with the annotations and slightly dilutes the sentence.

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 with zero parameters the surface area is minimal. The description adequately covers what the tool reports, though it omits any hint of when in a workflow an agent should invoke it.

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; there is no parameter semantics to clarify and the schema is trivially complete.

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+resource: describing China supplier checking capabilities with optional on-site verification in Shenzhen. It is distinguishable from get_sourcing_capabilities by naming the specific checking/verification domain, though it never explicitly contrasts the two capability-listing 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?

No when-to-use guidance, no mention of alternatives, and no stated prerequisites or trigger conditions. The agent must infer that this is the tool to call before deciding on a supplier check, but nothing in the text says so.

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 it as a non-read-only, open-world, non-destructive, non-idempotent action, and the description meaningfully adds that submission triggers human review rather than automatic scheduling. That is real behavioral context beyond the annotations, though is not explained how the confirm_submission gate interacts with that review.

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 compact sentences with the core action front-loaded and the human-review caveat following. No filler, though the 'Include the...' sentence is slightly underspecified rather than wasteful.

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 explanation is not required, and the human-review behavior is disclosed. However, with 6 fully undocumented parameters and an unexplained confirm_submission gate, the definition is not complete enough to invoke confidently without guessing at field intent.

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 0% across six parameters, so the schema carries no meaning at all. The description loosely maps 'questions, contact person and meeting details' to task/contact/subject/location but leaves subject, language, location and confirm_submission unexplained.

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 concrete verb and resource ('Request an in-person Shenzhen meeting with a supplier or seller') and specifies it is on the customer's behalf. It is distinguishable from siblings like request_supplier_check or shenzhen_errand, though it never names an alternative explicitly.

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 content guidance ('Include the questions, contact person and meeting details') but no when-to-use vs when-not-to-use framing against near siblings such as shenzhen_errand or request_on_site_check. Usage is implied by the purpose statement only.

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 it non-read-only, non-idempotent, open-world and non-destructive. The description adds meaningful operational context beyond that: customer liability for supplying valid codes/data, and the explicit non-scope (no issuing/legalizing/validating). It omits any note on downstream effects or timing, so not 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?

Two tight, front-loaded sentences: the action and scope come first, the liability/limitation clause second. Little wasted text, though the missing parameter explanation means the brevity is partly under-specification.

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 described. But for a 6-parameter request-submission tool with 0% schema coverage, the description leaves parameters wholly unexplained, which an agent needs in order to invoke 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 description coverage is 0% across 6 parameters and the description explains none of them (task, contact, subject, language, location, confirm_submission). 'Optional photo evidence' is mentioned but no photo parameter exists in the schema, so it does not compensate for the coverage gap.

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 verb-resource pair: requests organizing the application of customer-provided Chestny ZNAK marking codes/labels to goods in China before shipment. This is clearly scoped and cannot be confused with the sourcing/verification siblings, though it names no sibling explicitly.

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 context ('before shipment') and useful boundaries ('does not issue, legalize or validate marking codes'), which imply when to use it. However, it never states when NOT to use it in favor of an alternative, nor names a sibling tool, so usage is only implied.

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 a non-read-only, non-idempotent, open-world write, so the safety profile is covered. The description usefully adds that this spawns a human task rather than returning a claim, but says nothing about turnaround time, cost, or what confirm_submission gates.

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 free of filler. The disclaimer sentence earns its place as a scoping constraint.

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 described. However, with 0% parameter coverage and a two-step confirmation flow implied by confirm_submission, the agent lacks enough to invoke correctly in one pass.

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 0% across five parameters, so the description carries the full burden and does not compensate. task, contact, subject, language, and especially the confirm_submission flag are left entirely unexplained.

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 concrete verb and resource: requesting a real person to physically search Huaqiangbei for a component or product. The physical-market-search framing distinguishes it from verification siblings like verify_stock_on_site, though no sibling is named explicitly.

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 an offline market search is useful" gives clear triggering context, and "it does not claim stock or price" implicitly routes price/stock questions to request_market_price_check or verify_stock_on_site. No explicit when-not guidance or named alternative, 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?

Annotations already declare openWorldHint=true, non-read-only, non-idempotent, non-destructive, so the mutating external-request nature is covered. The description usefully adds that quotes are observations rather than guaranteed prices or availability, which is real value. However, it says nothing about the confirm_submission flag, expected turnaround, or that the request is dispatched to a human/agent workflow.

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 a useful caveat; no filler. It is arguably too terse for the parameter surface it carries, 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, so return values need no explanation, but the description leaves the request lifecycle opaque: no mention of confirmation, dispatch, or what contact/subject/location control. For a six-parameter, open-world request tool this is under-specified.

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 0% across six parameters, and the description explains none of them. The meaning of task, contact, subject, language, and especially confirm_submission (a boolean defaulting to false) is left entirely to inference, which is a significant gap for a 6-param tool.

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 concrete verb and resource: requesting collection of offline seller quotations, scoped geographically to Shenzhen. It distinguishes itself from capabilities like verify_stock_on_site or request_on_site_check by emphasizing quotations rather than verification, though it doesn't name those siblings explicitly.

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 guidance on when to prefer this over request_huaqiangbei_search, request_on_site_check, or verify_seller_claim, all of which overlap in the sourcing space. The intended usage is only implied by the word 'quotations'.

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 disclose the write nature and non-idempotency (readOnlyHint=false, idempotentHint=false, openWorldHint=true). The description adds genuinely useful context beyond them: this 'creates a request for review' and 'does not automatically schedule or guarantee that a visit will occur', which tells the agent the call is a non-final submission whose outcome is uncertain. It stops short of mentioning the confirm_submission step or any auth/handling details.

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 sentences, no filler, with the action stated first and the important caveat second. Every sentence earns its place and nothing is repeated from the name or annotations.

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 write tool with 0% schema description coverage, the description omits parameter meaning, does not mention the confirm_submission gate, and does not route between this and submit_supplier_check. Having an output schema excuses it from explaining returns, but the input-side gaps remain substantial.

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 0% across 5 parameters, so the description carries the full burden and does not meet it. It gives no meaning for 'request', 'contact', 'language' or 'confirm_submission', and 'supplier' is only obliquely covered by the list of visit targets. An agent must guess what to put in three required fields.

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: 'Request a human physical visit to a supplier, seller, office, shop, market counter, warehouse or address in Shenzhen.' That is far more precise than a generic 'on-site check' and an agent can tell it is a request/visit tool rather than a lookup. It does not, however, differentiate itself from the near-namesake sibling submit_supplier_check, so the boundary between them stays implicit.

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 or when-not-to-use guidance is given. With submit_supplier_check and get_supplier_check_capabilities in the sibling set, an agent has no stated rule for choosing this tool over those; the only implied trigger is 'you want a physical visit'. No prerequisites or sequencing are mentioned.

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 the safety profile (not read-only, open-world, not idempotent, not destructive). The description adds genuinely useful scope disclosure beyond that: it does not provide customs clearance and does not guarantee admissibility, classification, duties or regulatory approval. It still omits any mention of the confirm_submission gating 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?

Three sentences are front-loaded with purpose first, then scope, then disclaimers. The disclaimer sentence is dense but every clause earns its place by bounding liability.

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 described. Purpose and scope limits are covered, but with 5 fully undocumented parameters and a non-obvious submission-confirmation flag, the description leaves meaningful gaps for correct invocation.

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 0% across 5 parameters (task, contact, subject, language, confirm_submission). The description never explains what any parameter should contain, so it fails to compensate for the total absence of schema-level documentation.

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 verb+resource: 'Request support organizing documented legal export from China and compliant import, primarily for Russia/Belarus.' It clearly distinguishes this from sourcing/supplier-check siblings by scoping to legal import/export logistics support, though it does not name a specific sibling it replaces.

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 context is implied through the geographic and legal scope ('primarily for Russia/Belarus', 'documented legal export'), but there is no explicit when-to-use vs when-to-use-an-alternative guidance or prerequisites such as permissions or lead times.

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, openWorldHint=true, and idempotentHint=false, so the write/open-world profile is covered. The description adds one genuinely useful non-annotation trait — the human review gate before acceptance — but omits cost, timing, and what confirm_submission actually triggers.

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 sentences, front-loaded with the core action and followed by the review constraint. Efficient with little waste, though the long enumerated list could be tightened.

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 described, but for a 6-parameter submission tool with zero schema descriptions, the definition leaves required-vs-optional intent and the confirm_submission flag unexplained. The human-review note helps but is not 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 0% across 6 parameters, so the description carries the full burden. The task examples loosely map to the 'task' field, but contact, subject, language, location, and especially the confirm_submission boolean are left entirely unexplained.

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 ('Request a custom physical task in Shenzhen') and enumerates concrete task types (visit, ask questions, photograph, collect/deliver, obtain catalogue). However it does not differentiate itself from overlapping siblings such as collect_or_deliver_sample or request_on_site_check, which cover some of the same errand types.

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 task examples imply when this generic errand tool applies, and 'Human review is required before acceptance' signals a submission workflow. But there is no explicit when-to-use versus the many specialized siblings, and no stated prerequisites for choosing this catch-all over them.

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 is a non-read-only, non-idempotent, open-world write, so the safety profile is covered. The description adds genuine value by stating the side effect (one sourcing request created) and what is NOT committed (no purchase, no availability, no pricing). However, it omits the important behavioral fact that the confirm_submission flag (default false) gates the submission.

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 action and scope, and each sentence carries distinct information (what it does, the side effect, the non-guarantees). No 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?

An output schema exists so return values need not be described, and annotations cover the safety profile. What is missing is any handling of the required email/items inputs and the confirm_submission confirmation step, which an agent needs to call this mutation successfully.

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 0% across 6 parameters, and the description mentions none of them – not email (required), items structure, notes, company, or the confirm_submission gate. The description therefore does nothing to compensate for the undocumented 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+resource ('Submit a multi-line electronic component BOM') plus the destination of the action ('human sourcing in Shenzhen'). The phrase 'one sourcing request for the complete BOM' implicitly separates it from the single-component submit_component_rfq sibling, but neither sibling is named explicitly.

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 use this tool versus submit_component_rfq or the other submit_* siblings. The negative list ('does not purchase parts...') clarifies scope but does not guide selection between alternatives.

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, openWorldHint=true, and idempotentHint=false, so the write/external nature is covered. The description then adds genuinely useful context beyond the annotations: the request is reviewed by a named human (Maria Jurk), and it does not claim real-time inventory or invent pricing/availability, which sets correct expectations about latency and output reliability.

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 sentences, each earning its place: the action, the use case, and the behavioral caveat. The purpose is front-loaded and there is no filler 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?

With an output schema present, return values need no explanation, and the description covers the goal, the human-review path, and the honesty constraints. It is slightly thin on what the buyer should expect after submission (turnaround, acknowledgment), but nothing critical 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 every parameter is already documented in the schema with examples and defaults. The description adds no field-level meaning on top of that, which is the expected baseline of 3 when the schema carries the load.

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 and resource ('Submit an electronic component RFQ') and pins down the mechanism ('for human sourcing in Shenzhen, China'). It also clarifies the class of parts it targets, so an agent knows exactly what action it performs.

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 second sentence gives explicit triggering conditions: hard-to-find, obsolete, EOL, spot-market, BOM components requiring China sourcing. No sibling tools exist to contrast against and no when-not-to-use guidance is given, 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?

Annotations already declare openWorldHint=true, idempotentHint=false, and destructiveHint=false, and the description usefully adds that submission does not certify or guarantee the supplier, setting expectations about outcome. However, it says nothing about the confirm_submission flag (default false), which appears to govern whether the submission actually takes effect, nor about the human-review turnaround.

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 followed by the scope caveat and disclaimer. No filler, though the middle sentence about remote vs on-site checking is somewhat vague about how it maps to inputs.

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 no explanation. Still, for a non-idempotent, open-world submission tool with a confirmation flag and 0% schema coverage, the description leaves key operational details (confirm_submission, contact, language) unaddressed.

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 0% across six parameters, so the description carries the full explanatory burden. It loosely gestures at supplier, request (remote checking), and visit (on-site Shenzhen visit) but never names the parameters, and contact, language, and confirm_submission are entirely unexplained.

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 (submit) and resource (China supplier/seller) and clarifies the purpose is human verification, which separates it from read-only siblings like get_supplier_check_capabilities. It does not explicitly differentiate itself from request_on_site_check, even though it mentions on-site visits, leaving some overlap ambiguity.

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 implies when this tool applies (supplier needing human verification, optionally remote or on-site) but gives no explicit when-not conditions and never names the alternative siblings such as request_on_site_check or submit_component_rfq. Usage is inferable but not routed.

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 non-read-only, open-world, non-idempotent, non-destructive. The description adds genuinely useful context: it returns observations, not certification or a guarantee. But it omits operational traits an agent needs before triggering a dispatched physical task - that confirm_submission must be true to submit, that an external party is dispatched, and expected turnaround/response format.

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 sentences, front-loaded with purpose and followed by the scope-of-evidence caveat. No filler; well-sized, even though it under-serves the missing parameter documentation.

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 multi-step, open-world physical verification task with a submission-confirmation flag and zero schema coverage, the description is far too thin. It does not say a human/agent is dispatched, what the returned observations look like, or how to use confirm_submission - a caller would likely misfire the 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?

Schema description coverage is 0% across all six parameters, so the description carries the full burden and contributes nothing. It never explains what 'task' vs 'subject' vs 'contact' should contain, nor the critical role of 'confirm_submission' (defaulting to false) - an agent cannot safely populate any of these from the description alone.

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 (verify) and resource (a seller claim), scoping it to physical evidence in Shenzhen (office, warehouse, goods, packaging, ready stock). It is distinguishable from verify_stock_on_site (narrower) and request_on_site_check, though it never names those siblings to sharpen the boundary.

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 Shenzhen/factory-evidence framing implies when this tool applies, and the disclaimer 'not certification or a guarantee' sets expectations. But there is no explicit when-to-use versus request_on_site_check or verify_stock_on_site, and the ambiguity between those near-identical siblings is left unresolved.

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 is a non-destructive, non-idempotent write to an open-world service. The description adds real value beyond that by disclosing what the check does NOT establish (authenticity, ownership, total inventory), which prevents an agent from over-claiming the result. It says nothing about cost, turnaround time, or how confirm_submission gates the request.

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 action and scope, followed by evidence types and a limitation caveat. Every sentence carries information; only minor tightening would be possible.

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 6-parameter, non-idempotent submission tool with zero schema descriptions, the definition is thin: it omits the meaning of required fields (task, contact), the confirmation flow, and any relation to sibling tools. The existence of an output schema excuses it from describing return values, but the input and routing gaps remain.

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 0% across 6 parameters, so the description carries the full explanatory burden and largely fails. The evidence list (photos, labels, lot markings) loosely hints at what a "task" should contain, but task, contact, subject, language, location, and confirm_submission are never explained.

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 verb and resource: requesting an on-site human check of claimed stock in Shenzhen. It is clear on its own, but it never distinguishes itself from the near-identical sibling request_on_site_check or from verify_seller_claim/submit_supplier_check, so an agent cannot route between them from this text 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?

"Stock claimed to exist" implies the usage context (a claim needs physical verification), but there is no explicit when-to-use, when-not-to-use, or named alternative among the many similar siblings. The closing disclaimer defines scope boundaries rather than routing guidance.

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