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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds critical behavior: the plaintext key is returned only once ('平文は今回だけ返します'), which is essential for the agent to store it. It also implies each call adds a new key, not a replacement. No contradiction with 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?

Two sentences, zero filler. The core purpose and the one-time return are front-loaded, with the prerequisite in a parenthetical. Every 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 create operation with no output schema, the description covers the essential behavior (one-time return) and the prerequisite. It does not detail the response format or the exact location of the new key in the tenant, but these are minor given the annotations and schema cover the operation's safety profile.

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 all parameters have descriptions. The description adds meaning beyond the schema by explaining that api_key must be the key received at signup (the schema only says 'sk_live_…'). It also confirms environment defaults to live via the enum description, though this is already in 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?

Description states a specific verb (発行 = issue), the resource (API key), and scope (this tenant), and distinguishes it from siblings like create_avatar or create_session by naming the resource. It also clarifies live/test environments, making the purpose 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?

Clear context: this tool issues an additional API key, with an explicit prerequisite (api_key from signup) stated in parentheses. However, it does not explicitly say when not to use it or name alternatives; the distinction from siblings is implied by the resource type rather than stated.

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