Robozukan (ロボ図鑑)

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. With no output schema, the description usefully carries the return contract by enumerating what comes back (jaunt rationale, ports, sources, confirmation dates, related guides), which is genuine disclosure beyond the annotations. It omits error/not-found behavior.

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

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

Front-loaded with the return payload, followed by a short actionable instruction. Dense but every clause names a distinct returned field; no filler sentences, though the payload list is long enough to approach a wall of nouns.

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-only lookup with no output schema, the description supplies the return contents and the slug source, so an agent can call it correctly without further context. Missing only failure-mode behavior and any hint about output shape/structure.

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 schema already documents the slug format and example, so the baseline would be 3. The description adds real meaning by specifying where the slug originates (search_devices results), which affects correct invocation rather than just repeating 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 (返す/returns) and resource (1台のデバイスの銘板) and enumerates the actual payload: AI connectivity, autonomy rationale, ports, manual steps, sources/dates, and related guides. It implicitly contrasts with the sibling search_devices by telling the agent the slug comes from there, though it never explicitly says 'single device vs. list'.

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 closing sentence 'slug は search_devices の結果から取る' gives a clear prerequisite and workflow: run search_devices first, then fetch details for one device. No explicit when-not-to-use or exclusion is stated, so it stops short of a 5.

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

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

The annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds that the returned criteria cover two specific rating scales, but it does not describe the output format or whether the criteria are exhaustive, leaving a modest 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?

Two tightly written sentences with no filler. The core function is front-loaded, and the usage note follows immediately after.

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 reference lookup with no output schema, the description identifies the two rating dimensions and the intended use case. It is sufficient for an agent to call correctly, though it stops short of describing the exact return shape, which is a minor omission.

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, which is the baseline for a score of 4. There are no parameter semantics for the description to add 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?

The description states a specific verb and resource: it returns the judgment criteria for AI connectivity (AI-0–AI-5) and autonomy level (1–3). The scope is unambiguous and the sibling tools (get_device, list_guides, search_devices) cover unrelated domains, so no differentiation is needed.

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 this tool when explaining the meaning of the numeric ratings. That is clear usage context, and there is no competing sibling tool for rating criteria, but it offers no when-not or alternative guidance beyond this.

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 real behavioral context beyond that: results are returned newest-first and each entry carries title, summary, and URL. It does not mention pagination, list-size limits, or auth requirements, which keeps it short of a 5.

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

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

A single front-loaded sentence that states the resource, the returned fields, and the sort order with zero filler. Nothing is padded or repeated from 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 usefully declares what each list item contains (title, summary, URL) and the ordering, and the one optional parameter is fully covered by the schema. It stops short of noting whether the list is paginated or capped, which is the only remaining gap for a listing 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% and the single enum parameter is fully documented in the schema with per-value meanings. The description restates the three content types but adds no new syntax, defaults, or filtering semantics, so the baseline 3 for a well-documented schema 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 names a specific verb (一覧を...返す) and a specific resource set (機種別の接続ガイド・組み合わせレシピ・コラム), and also states the returned fields and ordering. Sibling tools (get_device, search_devices, get_rating_criteria) are all device/rating lookups, so this listing tool is unambiguous without needing to be named.

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: fetch the full corpus of guides/recipes/columns, optionally narrowed by category. The description never states when to prefer this over another tool, nor any exclusions (e.g., 'use this for browsing, not for text search'). Adequate but not explicit 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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: with no filters it returns the full set sorted by descending AI connectivity, which tells the agent what to expect from a bare call. It does not cover pagination/limit truncation behavior.

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

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

Three short sentences, no filler: the action and resource come first, the filterable fields second, and the default/ordering behavior last. Every sentence earns its place and the information is front-loaded.

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 usefully explains what a bare call returns (all devices ordered by AI connectivity), and annotations carry the safety profile. The only minor gap is that limit/pagination and the shape of returned records are not described, but for a 0-required-param search tool this is close to complete.

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 all five parameters and both enums. The description restates the filter semantics (partial match across product name/brand/summary, category, AI-rating floor, interface type) but adds little syntax or format detail beyond the schema, 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 gives a specific verb (検索) and resource (ロボ図鑑の収録デバイス) and enumerates the four filter dimensions, so an agent immediately knows this is a filtered-list tool. It never explicitly names the sibling get_device to draw the single-vs-many boundary, but the resource scope makes the distinction reasonably inferable.

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 states a concrete default behavior ('条件を省くと全件をAI接続性の高い順に返す'), which tells the agent this works with zero filters and how results are ordered by default. However, there is no guidance on when to reach for this over get_device or list_guides, and no exclusions are given; usage is only implied.

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