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

Annotations declare readOnlyHint=true, so the safe-read profile is already covered. The description adds that results come as 'document bundles,' which hints at the return shape, but says nothing about pagination, permissions, or availability of each bundle type.

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 with no filler; the verb and resource come first and the examples of document kinds follow efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two fully documented required parameters, no nested objects, and annotations covering the safety profile, the description supplies what an agent needs to select the tool. The lack of usage context relative to siblings is the only real shortfall.

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%, with both parameters documented and documentKind constrained by an enum, so the baseline is 3. The description only loosely restates the document kinds already enumerated in the schema and adds no format or constraint detail beyond it.

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 (Fetch) and resource (design application document bundles) and enumerates representative document kinds (amendment, refusal reason, decision packages). This lets an agent distinguish it from get_design_registration and get_trademark_documents, though it never explicitly names which sibling to prefer.

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 alternatives are named. The documentKind enum implies the tool is selected by document type, but the description does not state this or when to reach for it over the many 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=true, so safety is covered by structured data. The description adds nothing beyond that: no mention of what the response contains, whether the lookup returns historical priority claims, or how it behaves for an application with no priority right.

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 short sentence with zero waste and the purpose front-loaded, appropriate for a one-parameter read-only lookup. Being terse is not a defect here, though it leaves no room to disambiguate from siblings.

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?

The tool is simple: one fully described required parameter and a read-only hint, so the essentials are present. But with no output schema, the description carries the burden of explaining the returned 'priority-right information' and does not, leaving the agent guessing at the payload.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is well documented in the schema as a 10-digit Japan design application number. The description adds no format or semantic detail beyond that, 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?

The description pairs a specific verb ('Fetch') with a named resource ('design priority-right information'), which places it within the design-family siblings versus the trademark/patent equivalents. However, 'priority-right information' is domain jargon and the description never clarifies what that information actually is, so an agent cannot fully distinguish its payload from get_design_documents or get_design_registration.

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 routing to alternatives such as get_design_progress or the trademark/patent priority-right variants. The agent must infer everything 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?

readOnlyHint=true already tells the agent this is a safe read, so the annotation carries the safety profile. The description adds only the source ('official JPO API') and says nothing about what 'progress' data is returned, freshness, 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?

A single, front-loaded sentence with no wasted words. It is efficient, though its brevity comes partly from omitting useful context rather than from disciplined editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read tool with no output schema, the description is minimally adequate. It leaves open what 'progress' means relative to get_design_progress_simple and what the caller can expect back, which matters given no return-value documentation exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the single applicationNumber parameter is fully documented with a pattern and format hint in the schema. The description adds nothing 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 ('Fetch') and resource ('design prosecution progress'), which cleanly separates it from the trademark and patent progress siblings. However, it does not distinguish itself from get_design_progress_simple, which is the one sibling an agent could most easily confuse it with.

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 offers no guidance on when to use this tool versus the many alternatives, and it never mentions get_design_progress_simple. An agent must infer the choice 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 already declare readOnlyHint=true, so the safe-read nature is covered structurally. The description adds only that data comes from the official JPO API and is 'compact' – no disclosure of rate limits, auth requirements, or how compact differs from the full tool.

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 short, front-loaded sentence with zero filler. Nothing is redundant or 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 single-param read tool with full schema coverage and annotations, the essentials are present. But with no output schema and no explanation of what 'compact progress' contains, the agent cannot anticipate the response shape or how it differs from the sibling 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 coverage, and the schema documents the 10-digit pattern and Japan design application number semantics. The description adds nothing beyond the schema, so 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 ('Fetch') and resource ('design prosecution progress'), and the word 'compact' hints at a reduced-detail variant. However, it never explicitly distinguishes itself from the sibling get_design_progress, leaving the agent to infer what 'simple' drops.

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 exclusions, and no mention of the obvious alternative get_design_progress (or get_design_registration/documents). The agent gets no basis for choosing 'simple' over the full version.

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 readOnlyHint annotation already establishes this is a safe read, so the bar for the description is lower. It adds the useful detail that data comes from the official JPO API, but says nothing about rate limits, authentication, or error behavior when an application number is not found.

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 short sentence with no wasted words and the purpose front-loaded. It is efficient, though arguably too terse given the tool's role relative to its many siblings.

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 single-parameter read tool with annotations covering the safety profile and a fully documented schema, this is minimally adequate. With no output schema, the description could at least indicate what registration data is returned, and it gives no routing signal among the crowded sibling set.

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 applicationNumber parameter is fully documented in the schema, including the 10-digit pattern. The description adds no syntax, format, or semantic detail beyond that, so 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 clear verb+resource combination ('Fetch design registration information') and names the source (official JPO API). However, it does nothing to distinguish itself from siblings like get_design_documents or get_design_progress, which an agent could easily confuse with it.

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 offers no when-to-use guidance, no prerequisites, and no mention of alternatives among the many sibling tools. An agent must infer that this is the tool for registration-status lookups rather than documents or progress.

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 readOnlyHint annotation already signals a safe read operation, so the description doesn't need to restate that. It adds the useful context that the output is an 'official fixed address' (a permanent link), but omits the return format, whether the link is stable/expiring, and any failure behavior when an application isn't found.

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 with a clear verb and scope, no filler or redundancy. Every word 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?

With no output schema, the description should clarify what is returned (a URL string) and its stability, which it only gestures at with 'fixed address'. For a two-parameter read tool this is adequate but leaves a minor gap about the return value.

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 enum (patent/design/trademark) and the 10-digit application number pattern are fully documented in the schema. The description only restates the resource types, adding no syntax or format detail beyond the structured fields; 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 (resolve) and resource (official J-PlatPat fixed address/permalink) scoped to patent, design, or trademark applications. This distinguishes it from sibling tools that fetch documents, progress, or registration data, though it doesn't explicitly name a sibling it contrasts with.

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 implied by the name and purpose (look up a stable link for an application), but there is no explicit when-to-use, when-not, or pointer to alternatives such as the family/document tools. An agent can infer intent but 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=true, establishing this as a safe read. The description adds only 'from the official JPO API,' which is provenance rather than behavior — nothing about citation direction, result volume, pagination, or what happens with an unknown application number.

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, well-formed sentence with no filler, front-loading the verb and resource. It is efficient, though its brevity partly reflects under-specification rather than disciplined editing.

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 citation-retrieval tool with no output schema and minimal annotations, the description leaves the key semantic question — forward versus backward citations — unanswered, and gives no hint of return shape or coverage. A one-parameter tool needs little, but this omits the distinction that most affects correct use.

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?

Only one parameter exists and schema description coverage is 100%, with the schema documenting the 10-digit Japanese application number and its pattern. Per the baseline rule, the schema doing all the work warrants a 3; the description adds no format or edge-case detail beyond it.

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 (fetch) and resource (cited document information) scoped to a patent application, which separates it from siblings like get_patent_documents or get_design_documents. However, it does not clarify citation direction — whether these are documents the application cites or documents citing it — nor does it name any 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?

There is no guidance on when to use this tool versus the many adjacent siblings (get_patent_documents, get_patent_global_doc_list, get_patent_global_cite_class). The agent must infer that 'citations' is a distinct workflow from 'documents'.

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 readOnlyHint annotation already establishes this is a safe read operation. The description adds nothing further about behavior—no auth requirements, rate limits, response format, or what happens with invalid inputs—so it contributes almost no behavioral context beyond the 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?

The description is a single, front-loaded sentence with zero wasted words. It is appropriately concise, though its brevity reflects under-specification more than optimal structure.

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 tool with no output schema, the description should convey what information is returned or how it differs from related patent tools. Given the large sibling set and lack of return-value detail, the definition is too sparse to fully orient an agent.

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 schema has 100% description coverage for the single applicationNumber parameter, including its 10-digit Japanese format. Per the rubric, high schema coverage sets the baseline at 3 even when the description mentions no parameter details.

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 clear verb ('Fetch') and a specific resource ('patent divisional-application information'), which distinguishes it from sibling tools like get_patent_progress or get_patent_documents. However, the word 'information' is vague about what is actually retrieved, leaving the purpose at a minimum-viable level.

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 guidance on when to use this tool versus the many sibling tools, nor any prerequisites such as needing a valid Japanese application number. The description offers no context or exclusions.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds no behavioral context beyond that: it doesn't say whether the bundle is paginated, what a bundle contains, or any retrieval constraints, and there is no output schema to compensate.

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 efficient sentence with the resource front-loaded and no padding. It is appropriately sized, though it is too terse to be exemplary given the tool's role.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description partially compensates by naming bundle kinds, but it omits what a returned bundle actually contains and when to prefer this over sibling document tools. Adequate minimum but with clear gaps for a two-required-parameter fetch 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 coverage is 100%, so both parameters are already documented in the schema (including the 10-digit application number pattern and the documentKind enum). The description's bundle examples overlap the enum values and add no syntax or constraint detail, so 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 (Fetch) and resource (patent application document bundles) and enumerates concrete bundle kinds (amendment, refusal reason, decision). It does not, however, distinguish itself from close siblings like get_patent_jp_document or get_patent_global_document, leaving the agent to infer 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?

No when-to-use context, no prerequisites, and no mention of alternative document tools among the many siblings. The agent must guess when this is the right fetch tool versus get_patent_jp_document.

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 declare readOnlyHint=true, covering the safety profile. The description adds no behavioral context beyond 'Fetch'—no error behavior, return shape, or constraints on the relation parameter. With annotations carrying safety, this is minimal added value.

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 with no filler; it is appropriately sized for a simple read tool. Structure is direct.

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 read-only tool with full schema coverage and no output schema, the one-liner is functional. However, it omits the relation parameter and fails to distinguish this from get_patent_family_list, leaving a routing 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?

Schema description coverage is 100%, and the schema documents both relation (enum application/publication) and caseNumber. The description's 'by case number' adds no syntax or format detail beyond the schema, so 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 ('Fetch') and resource ('patent family record'), scoped by case number. It does not differentiate from the sibling get_patent_family_list, so an agent cannot tell whether this returns a single record or a list without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or conditions for choosing this over get_patent_family_list. The description only identifies a required input, not the context in which the tool applies.

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, so the read-only nature is covered. The description adds nothing beyond that – no pagination, result ordering, size limits, or auth/scope context – so it carries no behavioral value of its own.

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 efficient sentence with the key scoping idea front-loaded and no waste. It is perhaps overly terse given the available space, but nothing is redundant.

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 two-parameter read tool with full schema coverage and readOnly annotations, the essentials are present. It falls short by not distinguishing itself from the get_patent_family sibling or clarifying output expectations (no output schema).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with both parameters documented (relation enum and caseNumber). The phrase 'by case number' loosely references caseNumber but adds nothing beyond the schema, 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?

The description states a specific verb (fetch) and resource (patent family list) and a scoping key (by case number). However, it does not differentiate from the near-identical sibling get_patent_family, leaving the agent unable to tell which to pick without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or alternative routing is given. With a sibling named get_patent_family, the absence of any disambiguation is a clear gap.

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

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

The readOnlyHint annotation already establishes that this is a safe read, and the description adds nothing beyond that: no return shape, no mention of whether the class data may be empty for some publications, and no note on rate limits or lookup failure behavior. The description carries no value over the 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?

A single short sentence with no filler and the verb front-loaded. It is efficiently sized, though that brevity comes at the cost of substance rather than being a model of tight expression.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only a readOnly annotation, the description is the sole channel for explaining what 'global citation class' data an agent receives and in what form. It leaves that entirely unaddressed, so an agent cannot predict the response or confirm this is the right sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is documented with a concrete format example ('JP.12345678.A'), so the schema does the heavy lifting. The description contributes no additional parameter meaning, which matches the baseline 3 for fully-covered schemas.

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 largely restates the tool name: 'Fetch patent global citation class information' is a verbatim rewording of 'Get Patent Global Citation Class'. It never explains what a 'citation class' actually is or how this differs from siblings like get_patent_citations or get_patent_global_doc_list, so an agent cannot distinguish the resource on substance.

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, when not to, or which sibling to prefer for adjacent needs (e.g. general citations vs. this class-specific call). The only implied guidance is the single required applicationNumber, which is insufficient routing information.

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, so the safe-read profile is covered structurally. The description adds no behavioral context of its own: nothing about what the 'list' contains, whether results are paginated or bounded, or how the global scope differs from the other patent document endpoints.

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 short sentence with no wasted words, and it is front-loaded. However, it is concise by omission rather than by discipline: the brevity comes from under-specification, which leaves the definition thin rather than efficient.

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 lookup tool with no output schema, the description should at least say what the returned document list represents and how it relates to the sibling document endpoints. Neither is provided, so an agent lacks enough to call this confidently over its near-duplicates.

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 one well-documented parameter with 100% schema description coverage (applicationNumber with a format example), so the schema carries the load and the baseline is 3. The description contributes no additional parameter meaning, so it cannot rise above the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb ('Fetch') and a resource ('patent global document list'), so the basic purpose is clear. But it adds nothing beyond the title and does not distinguish this from close siblings like get_patent_global_document, get_patent_documents, or get_patent_jp_document, so an agent cannot tell which one to pick without reading schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of the alternative document-listing tools in the sibling set. The agent is left to infer usage entirely from the name.

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 readOnlyHint annotation already tells the agent this is a safe read, and the description adds nothing beyond that: no error behavior for unknown IDs, no indication of whether the document body or only metadata is returned, and no rate/format notes. It neither contradicts nor enriches the 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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though its brevity is partly under-specification rather than tight editing.

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 two-required-parameter fetch tool with no output schema and only a readOnly annotation, the description leaves too much unstated: what a 'global document' contains, why applicationNumber is required, and how it differs from the other patent document tools. The structured fields do not compensate for these 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?

Schema coverage is 100%, so both parameters are documented in the schema, which sets the baseline at 3. The description mentions only the document ID ('by document ID') and omits the equally required applicationNumber, so it adds no meaning beyond the schema and mildly under-represents the inputs.

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 (Fetch), resource (patent global document), and cardinality (one), which contrasts implicitly with the list sibling get_patent_global_doc_list. However, it never explains what 'global' means relative to get_patent_documents or get_patent_jp_document, so the agent cannot confidently distinguish it from those 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?

The description gives no when-to-use guidance, no preconditions, and names no alternatives. With many patent document siblings (get_patent_documents, get_patent_jp_document, get_patent_global_doc_list), this omission leaves routing entirely 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?

readOnlyHint=true already tells the agent this is a safe read, and the description only confirms that with 'Fetch'. It adds no behavioral context such as authentication scope, whether the document body or metadata is returned, or any rate/size limits, so it does little beyond the 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?

A single front-loaded sentence with no filler or redundancy. It is arguably too terse for a tool with two required parameters, but there is no wasted language.

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 annotated read with full schema coverage and no output schema, the description is close to sufficient, but it omits the required applicationNumber parameter entirely and gives no hint of what 'document' means in the response. An agent could attempt a call missing a required argument.

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 both documentId and applicationNumber (with format example 'JP.12345678.A'). The description only names the document ID and adds no syntax or format meaning, 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 ('Fetch') and resource ('patent Japan document') scoped by document ID, which is clearer than a bare 'get document'. However, it does not distinguish this tool from close siblings like get_patent_documents (plural) or get_patent_global_document, so an agent still has to infer which one applies.

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 routing to alternatives such as get_patent_documents for listing or get_patent_global_document for non-JP records. The single word 'one' hints at a single-record fetch but that is implicit, not stated.

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 declare readOnlyHint=true, so safety is covered. The description adds nothing beyond that — no note on how 'relation' changes the resolution, no response shape, no failure mode when the number cannot be resolved. Minimal but not contradictory.

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 short sentence, front-loaded and free of padding. It is efficient, though arguably too terse to earn full marks given the complexity of PCT number resolution.

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 number-resolution tool with two required params and no output schema, the definition omits how the enum relation alters behavior, what is returned, and what happens on failure. With no output schema and a specialized domain, the description should carry more of that burden.

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%, which sets the baseline at 3. The description adds no meaning beyond the schema — it never explains what the 'relation' enum values signify for resolution behavior or what format caseNumber expects.

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 verb (Resolve) and resource (PCT national phase application number), so purpose is identifiable. However, it is vague about what 'resolve' produces (a number lookup? a mapping?) and does not differentiate from siblings like lookup_number_relation or get_patent_divisional_app_info.

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 nothing about when this resolution path applies versus the sibling lookup_number_relation. The agent must infer usage entirely.

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?

readOnlyHint=true already tells the agent this is a safe read, and the description adds nothing beyond it — no indication of what data is returned, latency, pagination, or coverage limits. For a retrieval tool with annotation coverage the bar is lower, but zero added context leaves it 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 front-loaded sentence with no filler or redundancy. Efficient, though its brevity borders on under-specification rather than concise richness.

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 with annotations and a fully covered schema, the description is minimally viable. It omits any usage context or explanation of the returned priority-right concept, but no output schema exists that would otherwise need explaining.

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 applicationNumber parameter is fully documented (10-digit Japan patent application number) in the schema. The description adds no additional meaning, so 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 ('Fetch') and resource ('patent priority-right information'), and the 'patent' qualifier distinguishes it from the design and trademark priority-right siblings. It does not, however, explain what priority-right information comprises or how it differs from the many other patent retrieval 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 guidance on when to use this tool, no prerequisites, and no named alternatives among the 25+ sibling retrieval tools. The agent must infer usage 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 already declare readOnlyHint=true, so safety is covered. The description adds the useful detail that data comes from the official JPO API (relevant for freshness/authority expectations), but says nothing about latency, rate limits, or response shape.

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 sentence, front-loaded with the core action and resource, with no filler. Nothing could be removed without losing 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 single-parameter read tool with full schema coverage and a clear readOnly annotation, the description is minimally sufficient. The notable gap is the lack of differentiation from get_patent_progress_simple, which an agent needs to pick the right sibling.

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 parameter is fully documented with pattern and format, so the schema carries the load. The description adds no parameter detail beyond what the schema already provides, making the baseline 3 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?

The description states a specific verb+resource ('fetch patent prosecution progress') and names the source ('official JPO API'). It does not differentiate from the obvious sibling get_patent_progress_simple, 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 guidance at all on when to use this versus get_patent_progress_simple or the other patent siblings. The agent is left to infer that the non-simple variant is the fuller one, which is exactly the kind of distinction an explicit sentence could settle.

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?

readOnlyHint=true already covers the safety profile, so the description only needs to add context. It does note the data comes from the official JPO API and is 'compact', hinting at a reduced payload, but says nothing about rate limits, auth, or what is trimmed versus the full sibling.

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 with no wasted words; the verb and resource lead 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?

No output schema exists, so the description should give some sense of what 'compact progress' returns. Saying it is compact is the only hint; an agent cannot anticipate the returned fields or how they differ from get_patent_progress.

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?

With a single parameter at 100% schema description coverage, the schema already documents the 10-digit format and pattern. The description adds 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?

States a specific verb (Fetch) and resource (patent prosecution progress) with a source qualifier (official JPO API). It does not explicitly explain how it differs from the sibling get_patent_progress, leaving the 'Simple'/'compact' distinction to be inferred from the title.

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 and no mention of the obvious alternative, get_patent_progress, nor any prerequisites for obtaining a valid application number. The agent must guess at the selection criteria between this and its near-identical sibling.

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?

readOnlyHint=true already establishes this as a safe read, so the description need not restate that. It adds the provenance detail that the data comes from the official JPO API, which is mild but genuine context (authoritative source vs. derived data). It says nothing about rate limits, caching, or failure modes when the number is not found.

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 short, front-loaded sentence with no filler; the verb and resource come first. It is efficient, though arguably so terse that the registration payload's scope is never hinted at.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only lookup with fully documented input and no output schema, the description is minimally sufficient. It leaves open what 'registration information' actually comprises (registration number, date, status), which the agent cannot recover from annotations or schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the single parameter is documented with type, required flag, and a regex pattern plus 'Japan patent application number (10 digits)'. The description adds no format or interpretation detail beyond the schema, 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 ('Fetch') and resource ('patent registration information') plus the data source ('official JPO API'), which cleanly separates it from the trademark and design registration siblings. It does not distinguish itself from other patent-family siblings such as get_patent_progress or get_patent_documents, but the resource 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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives among the roughly 27 sibling tools. The agent must infer from the tool name alone that this is for registration (not prosecution/progress/documents) data.

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?

readOnlyHint=true already establishes this as a safe read, and the description adds that results come as 'document bundles' covering amendment/refusal/decision packages. It does not disclose return format (files, links, PDFs), pagination, or size, which matters for a document-fetch tool.

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 with no filler. Minor ambiguity from 'such as', which suggests the listed kinds are examples while the schema enum is exhaustive.

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?

Two required params and no output schema mean the definition should clarify what a 'bundle' actually returns; that is absent. The core input contract is clear, but an agent cannot anticipate the response shape.

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 schema already documents both applicationNumber (10-digit JP format) and the documentKind enum. The description merely restates the enum values in prose and adds no format or constraint detail 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 specific verb ('Fetch') and resource ('trademark application document bundles') and enumerates the document categories available. It is distinguishable from the sibling get_patent_documents and get_design_documents by the trademark resource, though it never explicitly contrasts 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?

No guidance on when to use this versus the other trademark siblings (get_trademark_progress, get_trademark_registration), nor any prerequisites such as needing a valid application number first. Usage is only implied by the tool name.

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 annotation already declares readOnlyHint=true, and the description's verb 'Fetch' is consistent with that. But it adds no behavioral context beyond the annotation: no authorization needs, rate limits, return format, or error semantics are described.

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, front-loaded sentence with no wasted words. It is appropriately sized for a simple one-parameter lookup, though its extreme brevity borders on 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?

For a low-complexity, one-parameter read tool with full schema coverage and a readOnly annotation, the description is minimally adequate. It does not explain what priority-right information is returned or help route between the many sibling tools, but no critical calling information 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%, and the schema itself fully documents the single applicationNumber parameter including the 10-digit Japan trademark format. The description adds no parameter details, 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 states a clear verb ('Fetch') and resource ('trademark priority-right information'), so an agent can tell what the tool does. However, it does not distinguish this tool from closely named siblings such as get_patent_priority_right_app_info or get_design_priority_right_app_info; only the tool name carries that 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?

The description gives no guidance on when to use this tool versus alternatives like get_trademark_progress, get_trademark_registration, or the patent/design priority-right variants. It simply states the purpose, leaving context and exclusions entirely 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?

The readOnlyHint annotation already declares this as a safe read operation, so the description doesn't need to cover safety. It adds that the data comes from the official JPO API, which is useful context for trust and data freshness, but it doesn't describe response format, error behavior, 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?

The description is a single, efficient sentence that is front-loaded with the action and resource. It is appropriately sized for a simple tool, though it could be slightly more informative without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with one fully described parameter and no output schema, the description is minimally adequate. However, it fails to mention the existence of get_trademark_progress_simple or explain what 'prosecution progress' entails, leaving gaps in understanding the tool's scope.

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 single parameter applicationNumber is fully documented in the schema with its pattern. The description adds no additional meaning beyond what the schema provides, which is acceptable when schema coverage is high.

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 (Fetch) and resource (trademark prosecution progress) with the data source (official JPO API). However, it does not differentiate from the sibling get_trademark_progress_simple, leaving ambiguity about which progress tool to use when.

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 is provided on when to use this tool versus the 'simple' variant or any other sibling. The agent must infer usage from the name alone, which is insufficient given the presence of a closely named alternative.

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?

readOnlyHint=true already tells the agent this is a safe read. The description adds that the output is 'compact' and comes from the official JPO API, but never says what compact omits relative to the full tool or whether results are cached/paginated. Useful but thin context beyond 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?

A single efficient sentence with the resource and source front-loaded and no filler. It is arguably too short to be maximally useful, 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?

For a one-parameter read tool with no output schema and annotation-covered safety, this is minimally adequate. It omits what 'compact' progress actually returns, which is the one thing that would help an agent choose it over get_trademark_progress.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the 10-digit pattern documented in the schema itself, so the parameter is fully specified without the description. The description adds nothing about the applicationNumber format, so 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 ('Fetch') and resource ('trademark prosecution progress') and identifies the source ('official JPO API'). The word 'compact' hints it is the lightweight variant of get_trademark_progress, but it never names that sibling, so differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance and no mention of the sibling get_trademark_progress, which is the obvious alternative. An agent must guess that 'simple/compact' means use this when a slim payload is preferred.

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, so the read-only nature is covered. The description adds only the source (official JPO API); it says nothing about return format, error behavior when an application number is not found, 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?

One short, front-loaded sentence with no filler. It is efficient, though it could carry a little more routing or return-shape information at negligible cost.

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 single-parameter read-only lookup with 100% schema coverage and no output schema, the description is minimally viable, but it omits what the fetched registration data contains and how failures are surfaced, which would help an agent call it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single applicationNumber parameter is fully documented (10-digit Japanese format) in the schema itself. The description adds nothing beyond the schema, so 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 (fetch) and resource (trademark registration information) plus the data source (official JPO API). It is clearly distinct from progress/documents siblings by naming registration, 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?

No guidance on when to use this tool versus alternatives like get_trademark_progress or get_trademark_documents. The agent must infer the selection criteria 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?

The readOnlyHint=true annotation already establishes the safe-read profile, so the description need not restate safety. Beyond that it only names the upstream API; it says nothing about what a 'relation' returns (e.g. a single number vs. a set), whether lookups can fail for unknown numbers, or any rate/coverage limits. With no output schema, this is a notable gap.

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 no filler and the key concept (resolving number relationships) front-loaded. It is efficient but arguably too terse to carry its weight.

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 three required parameters and no output schema, the description should explain what the resolution returns and in what form. It only identifies the source API, leaving the agent unable to predict the response shape or interpret relationType outcomes.

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 all three parameters carry enum constraints and descriptions, so the baseline of 3 applies. The description adds no syntax, format, or edge-case detail beyond what the schema already states.

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 and resource ('Resolve official case number relationships') and names the data source ('JPO case number reference API'), so the agent knows it is a reference-resolution utility. It does not, however, distinguish itself from siblings like get_patent_family or resolve_applicant_code, nor does it explain what a 'relationship' actually yields.

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 named alternative among the 25 sibling lookup tools. The agent must infer from the name alone that this is for translating one case number into its related numbers.

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?

readOnlyHint=true already declares this is a safe read. The description adds that it uses 'official JPO applicant endpoints,' which is somewhat useful context. However, it doesn't disclose error behavior for invalid codes, rate limits, or what happens on ambiguous matches.

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, efficient sentence that front-loads the bidirectional resolution capability with no wasted words.

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 3-required-parameter lookup tool with no output schema, the description could explain the return format (name string vs code string) and edge cases. It covers the core purpose but leaves gaps an agent might need, though annotations and the complete schema carry much of the load.

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 fully documents all three parameters including enum values and the 'name: applicant string, code: applicant code' semantics. The description adds no parameter detail beyond what the schema provides. Baseline 3 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 bidirectional verb+resource: resolve applicant code to name or name to code via JPO official endpoints. Clear purpose, though it does not explicitly distinguish itself from sibling lookup tools like lookup_number_relation.

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 to use it (when you have one identifier form and need the other), but gives no explicit when-to-use vs alternatives, no prerequisites, and doesn't mention the sibling lookup_number_relation which seems related.

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