Esprit Delasse

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety and scope profile is largely covered. The description adds that the read is scoped to a single domain and returns the full body text, but says nothing about request cost, limits, failure modes, or whether the site must be pre-loaded/crawled.

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 returned, followed by the parameter note and the usage trigger. Every sentence carries information, though the parameter sentence largely duplicates the schema and could be trimmed.

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

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

An output schema exists, so return-value detail is not the description's burden. Purpose, accepted parameter forms, domain scope, and the accuracy-critical use case are all covered; only limits on very long pages or preconditions are unaddressed.

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

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

Schema description coverage is 100% for the single id parameter, which already documents that a search-result id, URL, path, or Japanese-language form is acceptable. The description restates exactly the same accepted forms, adding 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 and resource: returns the full body text of a page on the Esprit Delasse site. The emphasis on 全文 (full text) implicitly distinguishes it from siblings like get_page or search, but no sibling is named explicitly, so the differentiation must be inferred from context.

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

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

Gives a concrete when-to-use trigger: verify prices, dates, conditions, and terms against the page body before answering. It does not, however, say when to prefer this over get_page or search, so the agent must derive the division of labor itself.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds real behavioral context beyond that: this is a deprecated/legacy alias and its response format differs from fetch. It stops short of saying anything about rate limits, caching, or what the differing shape actually looks like.

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

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

Three short sentences, front-loaded with the legacy status and the routing advice, with essentially no filler. The only mild redundancy is restating the 'different shape than fetch' idea, but the structure is 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?

There is no output schema, and the description notes the return format differs from fetch without describing it, which is a small gap for a tool the agent might still call. For a deprecated alias whose guidance is 'use fetch instead', the coverage of purpose, status and route-away is otherwise sufficient.

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

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

Schema description coverage is 100% and the single parameter (url) is documented in the schema, including that Japanese-language URLs/paths are acceptable. The description adds no further meaning about the parameter, 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 that get_page returns a page's body like fetch but in a different format, and identifies itself as a retained legacy name ('以前の名前') for esprit-delasse.com. That is a concrete verb+resource plus a clear distinction from the sibling fetch. It is slightly less specific than ideal because the actual output shape is never characterized.

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 explicitly says to use fetch for new work ('新しく使うときは fetch を使ってください') and explains that get_page is kept only for clients already connected to it. Both the when and the when-not are stated, with the alternate tool named.

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

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

Annotations already declare the safe read-only profile, so the description only needs to add context beyond that. It usefully discloses pagination behavior (50 per page, capped at 200, offset to continue) and that only loaded/fetched pages are listed, which is real behavioral detail not present in the annotations.

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

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

Three sentences, front-loaded with the return content, then pagination mechanics, then the usage cue. Efficient and well ordered, with no filler.

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

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

For a simple read-only list tool with no output schema, the description covers what is returned (titles and URLs), pagination, and the selection cue, while annotations cover safety. An agent has enough to call it correctly; only explicit sibling routing 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 0%, so the description carries the burden and does add meaning: limit is the per-call count (max 200) and offset retrieves the continuation. It doesn't mention the default of 50 explicitly as a default or the minimum of 1, but the core semantics of both parameters are conveyed.

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

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

States a specific verb+resource: returns a list of pages on esprit-delasse.com with title and URL. The scope (loaded/fetched pages) is concrete, though sibling differentiation is only implied via 'find what pages exist / when search fails' rather than naming search or search_pages.

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

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

Gives a usage context ('when you want to know what pages exist, or when searching and can't find something'), which hints that search is tried first. However, it never names the alternative tools (search, search_pages, site_overview) or states when this is the wrong choice, so guidance remains implicit.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds meaningful context beyond that: scope is limited to already-loaded pages, excludes the open internet and post-load updates, and prescribes a specific fallback behavior when nothing is 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?

Purpose and scope are front-loaded in the first sentences, followed by usage and fallback guidance. It is a fairly dense block with some repetition of the 'not found' theme, but every sentence carries actionable instruction rather than filler.

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

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

An output schema exists, so return values need not be explained, and the description adequately covers scope, activation, and failure handling. The remaining gap is the unresolved overlap with the sibling 'search_pages', which the description never addresses.

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 'query' parameter is documented with an example, so the baseline is 3. The description adds query-construction guidance beyond the schema (rephrase with full names or synonyms when a first attempt fails), which enriches how the parameter should be used.

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

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

States a specific verb and resource: search loaded pages from esprit-delasse.com by keyword and return matching excerpts with URLs. The scope constraint (only loaded pages) is explicit. However, it never distinguishes itself from the very similar sibling 'search_pages', so an agent cannot confidently choose between the two from the description alone.

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

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

Gives clear activation context ('if asked about Esprit Delasse, use this first') plus failure handling (rephrase, use full names or synonyms, read candidate pages, and refuse to guess). It provides strong when-to-use guidance but never names alternative tools like search_pages or fetch, so it stops short of full alternative 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, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds the useful fact that the return shape differs from 'search' and that this is a deprecated alias, but it does not say how the return format differs or note the limit cap.

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 with the legacy/deprecation status front-loaded, followed by the behavioral note and the redirection to 'search'. Efficient and well-ordered, though slightly repetitive in restating the 'former name' framing via 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?

With no output schema, the description carries the return-value burden, and here it only says the return format 'is different' without explaining it - which is precisely the information an agent needs to choose between this and 'search'. The tool's core distinction is left unspecified.

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 only 50%: 'query' is documented with an example, but 'limit' has no description at all. The description provides no parameter guidance whatsoever, so it fails to compensate for the undocumented 'limit' parameter or its 1-20 range.

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 this searches within the site, identifies it as a legacy alias of the 'Esprit Delasse' feature, and explicitly distinguishes itself from the sibling 'search' by noting the different return format. The purpose is clear, though the actual behavior is deferred to 'same as search' rather than described directly.

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

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

It gives an explicit condition for use ('kept for those who are already connected'), names the alternative ('search'), and states the directive 'when using it newly, use search'. When-to-use and when-not-to-use are both spelled out with the alternative tool.

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, openWorldHint=false, destructiveHint=false, so the safety profile is covered. The description adds the otherwise-missing return field list (type, description, page count, main pages), which is genuinely useful given there is no output schema. It has no params, so it is effectively scoped to one fixed site, though that is left implicit.

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, each doing work: what it returns, which fields, and when to call it. Front-loaded with the return value and no filler.

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

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

Adequate for a parameterless, read-only inspection tool whose annotations cover safety and which helpfully lists its return fields in absence of an output schema. It could note that the tool is bound to a single predetermined site, but an agent can operate it correctly as written.

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?

Zero parameters, so the baseline of 4 applies. Schemas coverage is 100% and there is nothing extra for the description to explain.

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

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

States a concrete verb (return info about a site) and enumerates the specific content returned: type, description, loaded-page count, and main pages. This distinguishes it in effect from fetch/get_page/list_pages/search, though it never names a 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?

"最初にサイトの全体像をつかみたいときに使います" gives a clear triggering condition (first, whole-site orientation). It offers no exclusions or named alternatives, so it stops short of a 5.

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