nice to have

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds genuinely useful return-shape detail beyond that, notably that only 'the first three decisions' are included, warning the agent that output is partial. It does not cover pagination, errors, or whether lang affects results.

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

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

Two tight sentences: capability and return contents first, usage routing second. Slightly padded by the vague domain phrase 'nice to have kit', but nothing is wasted overall.

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 does so by listing the fields an agent will receive, including the truncation to three decisions. The lang parameter remains unexplained, which is the main gap for a 2-parameter 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 50%: id is documented with an example ('deck-16x9'), but lang is undocumented in both schema and description. The description only restates the 'by id' lookup and adds nothing about the lang parameter or how it affects output.

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 the details of one ... kit by id') and enumerates what is returned (purpose, first three decisions, requirements, fixes). The 'one kit by id' scoping clearly separates it from list_kits and search_kits.

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?

Explicitly says 'Use after search_kits to explain a kit to the user,' giving a clear workflow position and intent. It does not state when not to use it or what to do instead for bulk retrieval, but the sequencing guidance is concrete.

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 is covered. The description adds the scoping constraint and the return fields, but says nothing about result size, pagination, or whether the shelf contents are dynamic — useful context that is left out.

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 front-loaded sentence: verb, scope, then the returned fields in parentheses. No filler, nothing redundant, every element 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 simple read-only list tool with no output schema, the description covers the return shape and scope adequately. However, it omits any explanation of the lang parameter and does not address result volume, leaving minor but real 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 description coverage is 0% and the single lang parameter (enum ja/en) is never mentioned in the description at all. Because the schema does not document it either, an agent gets no explanation of what 'lang' localizes or when to pass it, so the description fails to compensate for the coverage gap.

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

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

States a specific verb (List) and resource (kits), plus a scope qualifier (nice to have shelf) and the returned fields (id, name, description, page URL). It distinguishes itself implicitly from search_kits by being an unfiltered enumeration, but never names the 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?

The word 'every' implies this is the exhaustive-enumeration option, which contrasts with search_kits, but no when/when-not condition or alternative is stated. Usage must be inferred from the verb rather than read.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower. The description adds genuinely useful context: it works in Japanese or English, the corpus is a curated shelf of kits, and it lists the kinds of topics covered. It omits return shape and result-count/pagination behavior, but adds clear value beyond 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?

Purpose is front-loaded in the first clause and the call-to-action follows immediately. The long em-dash list of example domains is somewhat sprawling, but each item illustrates the query space, so little of it is truly 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 two-parameter, read-only search with no output schema, the description covers when to use it, what corpus it searches, and bilingual query support. It does not describe the return format (kit list, identifiers for get_kit), which is the one remaining gap an agent would benefit from.

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 both parameters are already documented, giving a baseline of 3. The description reinforces the query semantics with concrete example prompts (「スライドを作りたい」etc.) and confirms bilingual input, but adds no syntax or format 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?

States a specific verb (Search) and resource (a shelf of ready-made build kits for Claude Code/Codex), and describes the content of the resource (step-by-step recipes with pitfall fixes). It does not explicitly name the siblings get_kit or list_kits, so an agent must infer the distinction, but the purpose itself 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?

Gives a clear trigger — 'Use this whenever the user wants to make or build something' — and states the intent, checking whether a kit already exists before starting from scratch. It stops short of naming alternatives (get_kit/list_kits) or saying when not to use it, so it is solid but not fully routing.

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