Nanukamachi MCP

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses that descriptions can be truncated and must be paged (a real behavioral trait beyond annotations), but says nothing about not-found behavior, name-vs-slug precedence, or locale effects on the returned content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences; the core retrieval purpose and returned fields come first, with the paging instruction second. 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?

It compensates well for the absence of an output schema by listing the fields returned, and it warns about truncation. The remaining gap is that zero parameters are marked required, yet the description never states that at least one of name or slug must be supplied.

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 all five parameters are already documented, including the nextOffset continuation hint. The description only restates the paging role of offset/maxChars and adds no meaning about precedence between name and slug or about how locale changes results.

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 and resource ("Get full details for one digital archive item"), states the two lookup keys (slug or name), and enumerates the returned fields. The singular "one ... item" implicitly separates it from search-archives, but no sibling is named, so differentiation is left to inference.

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?

Provides concrete usage for the pagination parameters ("Use offset and maxChars to page through long descriptions"), which is real when-to-use guidance. It gives no guidance on when to prefer search-archives over this tool, nor on what to do when a lookup fails or when both name and slug are supplied.

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 and openWorldHint=false, so safety and scope are covered. The description adds a paging model and the shape of returned content, but it does not say what happens when both name and slug are supplied, or when neither is (all parameters are optional), which matters for a lookup 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?

Two sentences, no filler, with the core purpose front-loaded and the paging hint placed after it. Every clause carries information an agent can act on.

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, listing the returned fields is exactly the right compensation, and the schema is fully documented. The remaining gap is the lack of any note that at least one of name or slug is effectively needed even though the schema marks nothing required, plus the absence of a pointer to list-parking for slug discovery.

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

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

Schema description coverage is 100%, so the baseline is 3; the description adds only the note that offset/maxChars exist to page through long descriptions and that either slug or name may identify the lot. Those are useful framing points but add little beyond the parameter descriptions themselves.

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?

A concrete verb-plus-resource statement ("Get full details for one parking lot by slug or name") that also enumerates the returned fields (fee, hours, surface, coordinates, canonical URL). It is clearly distinct from the list-parking sibling, though the description never names that sibling or explains that it is the way to discover slugs.

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 useful in-tool guidance for paging ("Use offset and maxChars to page through long descriptions"), which tells the agent how to handle oversized content. It stops short of true selection guidance: no mention of when to prefer get-spot or list-parking, and no statement of the prerequisite that a valid slug/name must exist first.

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 and openWorldHint=false, so the safety profile is covered. The description adds that the payload is a site overview containing routes and discovery documents, but says nothing about freshness, caching, or response shape of those discovery documents.

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 the verb first and no filler. 'Machine-readable discovery documents' is slightly opaque, but the sentence earns its place.

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

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

For a zero-parameter, non-destructive info tool with no output schema, naming the three categories of returned content (languages, routes, discovery documents) is enough for an agent to decide to call it. Only a brief note on what a 'discovery document' yields 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?

The tool takes zero parameters, so the schema carries no semantic burden and the baseline of 4 applies. The description correctly implies a parameterless call that returns a static site-level overview.

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 (Get) and resource (overview of Nanukamachi.com), then enumerates the content: languages, main routes, and machine-readable discovery documents. This clearly separates it from the domain-specific siblings like get-parking or search-archives, though it never names them 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?

The framing as an 'overview' implies it is an orientation/discovery entry point, but there is no explicit statement of when to prefer it over get-archive, list-spots, or the other siblings, nor any prerequisite or exclusion 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 establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavior: the full description is returned by default, and descriptionTruncated/nextOffset signal remaining text — valuable because there is no output schema.

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 what is retrieved and how it is identified, followed by paging behavior. No filler or restatement of the title.

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?

Covers identification, default return size, and truncation for a zero-required-parameter tool. It leaves unstated what happens if neither name nor slug is supplied, or if both are given and disagree, which is the main remaining 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 coverage is 100%, so the baseline would be 3. The description earns the extra point by explaining the relationship between offset, maxChars, and the nextOffset/descriptionTruncated continuation loop, which the schema descriptions only hint at.

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 ('Get full details for one spot') plus the two lookup keys, slug or name, and scopes it to Nanukamachi-dori. An agent can distinguish it from the list-spots sibling by the 'one spot' framing, 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?

Gives clear operational context: look up by slug or name, and page with offset/maxChars for long articles. It stops short of explicit exclusions such as when to prefer search or list-spots over a direct slug fetch, so it is clear context without routing rules.

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 and openWorldHint=false, covering the safety profile. The description adds useful context by enumerating the returned fields, but says nothing about pagination behavior, ranking, or what happens when query/category match nothing.

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 with zero filler, and the scope constraint is front-loaded before the return-field list. Every sentence contributes information.

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

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

With no output schema, the description appropriately enumerates the returned fields, and the rich input schema plus annotations cover the rest. Only minor gaps remain, such as whether results are distance-ranked or how many fields are localized per locale.

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 limit, query, locale, and category are already fully documented, including enums and defaults. The description adds no parameter-level meaning beyond the schema, which is the expected 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 gives a specific verb ("Search") and resource ("parking lots") and narrows the scope to a named area, Nanukamachi-dori. It also lists the return fields, so an agent can distinguish it from get-parking, but it never names that sibling or explains the relationship 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?

Usage is implied: use this to search/browse multiple parking lots and get-parking for a single one. There is no explicit when-to-use vs when-not guidance and no mention of the sibling tools, so the agent must infer the routing.

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 and openWorldHint=false, so the safety and closed-world profile is covered. The description adds real value by disclosing the return shape (slugs, names, categories, tags, summaries), which is meaningful since there is no output schema. It says nothing about result ordering, total counts, empty-result behavior, or how limit interacts with the search, so it is solid but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero filler. The capability and scope come first, the return payload second, which is exactly the right front-loading for an agent scanning tool definitions.

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 five optional parameters, no required inputs, and no output schema, the description covers the two things an agent most needs: what can be searched and what comes back. Only minor gaps remain, such as pagination semantics and whether results are ranked, which are low-risk for a read-only list 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 100%, including enum glosses for genre (eat/tabe/miru/yado) and locale, plus a concrete category example list. The description adds no parameter meaning beyond that, so the baseline 3 applies: the schema does all the semantic work here.

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 ('Search') plus the concrete resource types (shops, restaurants, cafes, sights, accommodation) and even pins the geographic scope to Nanukamachi-dori. It also enumerates the returned fields (slugs, names, categories, tags, summaries). It stops short of an explicit contrast with the singular sibling get-spot, so a 4 rather than 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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives. Nothing tells the agent that get-spot is the right tool once a slug from this list is in hand, or how this differs from get-archive or search-archives. Usage is only inferable from the name and the entity types 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 and openWorldHint=false, so the safety profile is covered. The description adds the returned field list, which is genuinely useful, but says nothing about ranking, empty-result behavior, or how query matching works across locales.

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, zero boilerplate, with the data source stated first and the return shape second. Every clause carries information.

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

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

With no output schema, listing the returned fields is exactly the right compensation, and the collection scope is stated. What is missing is any hint of result ordering or how to page beyond the 1-50 limit.

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 including the two enums is already documented; baseline 3 applies. The description adds no meaning beyond the schema, such as whether query matches names, categories, or descriptions.

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 (Search) and a specific resource (digitized historical postcards and printed materials from Nanukamachi-dori), plus the returned fields. It does not explicitly distinguish itself from get-archive, which an agent must infer returns a single record.

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 reference to any sibling tool. The reader must infer that this is the discovery path and get-archive is the detail path; nothing in the text says so, and there is no note on when to prefer category filtering over free-text query.

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