claim_key_transfer

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the mutation profile is partly covered. The description adds that the operation targets the caller's own existing key and originates from a device screen, but it never discloses that the code is presumably single-use/non-idempotent, what happens to the key on the source device, or what failure looks like for an expired or invalid code – material for a key-migration mutation.

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 sentence with no filler, where the code's origin is placed before the action it enables. Nothing is repeated from the schema or annotations and no clause could be cut without losing information.

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. However, for a security-relevant, non-idempotent key-transfer mutation in a suite that also offers check_key_transfer, the description omits the ordering with that sibling and any note on one-time codes or post-claim state, which an agent needs to sequence the call correctly.

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 0% and the only parameter is titled simply 'Code', so the description does the real explanatory work: it specifies the format (8 digits) and the exact source (the '別の端末に移行' screen on the smartphone), which is what an agent actually needs to source the value. It stops short of stating expiry, leading-zero handling, or whether the code is case/format-normalized.

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 and resource: requesting takeover of the user's existing encryption key (本人の既存暗号鍵の引き継ぎを要求する), and it pins the trigger to an 8-digit code shown on the phone's migration screen. That is enough to distinguish it in intent from the sibling check_key_transfer, though it never names that sibling explicitly, so the differentiation requires the agent to infer it from the wording.

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 only usage context given is the provenance of the code ('スマホの「別の端末に移行」に表示される8桁コード'), which implicitly tells the agent this is used during a device-migration flow. There is no explicit when-to-use, no exclusion, and no statement about whether check_key_transfer should be called first or when this should be avoided. Usage is implied rather than guided.

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