check_gtrconfig

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

No annotations are provided, so the description carries the full burden. It discloses that only Owner and Admin can access the tool, which is a behavioral constraint. However, it does not explicitly state whether the tool is read-only, whether it modifies anything, or any other side effects. It mentions returning a state (success, status), but not the full 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?

The description is reasonably structured with a title line, a note, argument list, and return section. It is relatively short and to the point, though the formatting includes line breaks and special characters that could be streamlined. Overall, it earns every sentence without much waste.

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 description mentions returned values as 'Gtrconfig状態（success, status）' but does not explain what 'success' and 'status' mean, nor does it clarify whether the actual content of Gtrconfig is returned. There is ambiguity about the tool's behavior when the configuration does not exist or on errors. Given the presence of an output schema (not shown), the description should complement it but falls short.

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 coverage is 0%, so the description must compensate. It explains project_path as 'プロジェクトのルートパス' (root path of project) and caller_agent_id as '呼び出し元エージェントID（必須）' (caller agent ID, required). However, the schema marks caller_agent_id as optional (default null), contradicting the description that says it is required. This inconsistency reduces clarity.

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 clearly states 'Gtrconfigの存在確認と内容取得' which translates to 'Check existence and get contents of Gtrconfig'. It specifies a specific verb and resource, and distinguishes from siblings like check_gtr_available (which likely only checks availability) and analyze_project_for_gtrconfig (which analyzes/generates).

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 includes a usage restriction: '※ Owner と Admin のみ使用可能' (Only Owner and Admin can use). However, it does not provide guidance on when to use this tool versus alternatives (e.g., check_gtr_available) or when not to use it. The sibling tools list includes similar tools, but no differentiation is given.

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