iCloud にサインイン

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

With no annotations, the description carries the full burden and does well: it discloses the side effect (a browser flow), the persisted artifact and its exact path (~/.mustdo/auth.json), and the human-in-the-loop prerequisite. It is silent on failure/timeout behavior and whether an existing token is overwritten, 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?

Three tight sentences: action, trigger, precondition. The routing constraint is front-loaded and every clause earns its place with no filler.

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-optional-parameter, no-output-schema tool, the description covers purpose, trigger, precondition, and side effect. Only minor gaps remain (failure/timeout handling, token-overwrite semantics), which are not essential for correct invocation.

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 only one optional parameter exists, so the schema already fully documents waitSeconds (default 90, range 5-300). The description adds no parameter syntax or defaults beyond that, making the baseline 3 correct.

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 (opens Apple's sign-in page, persists ckWebAuthToken to ~/.mustdo/auth.json). This is unmistakably different from every sibling tool, all of which are todo operations, so an agent can route to it without ambiguity.

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 an explicit trigger (when another tool returns NOT_SIGNED_IN) and an explicit exclusion (call only when the user can operate the browser). Both the when and the when-not are stated, leaving nothing to inference.

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