agent_auth

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 that Aiterm only extracts commands/URLs while credentials are persisted solely by each CLI, and it documents the state machine (waiting → input_required → authenticated). It omits any failure/timeout or permission behavior for start/cancel, keeping 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?

Front-loaded with the purpose statement, then proceeds through ownership, human-in-the-loop flow, state semantics, and remote support in compact sentences. Dense but each sentence carries distinct information; 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?

An output schema exists, so return-value explanation is not required, and the description still usefully defines the waiting/input_required/authenticated statuses. For a credential-touching start/cancel tool with no annotations, the main gap is absence of error/failure guidance and permission/prerequisite notes.

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 only 50%, so the description should compensate more than it does. It adds meaning for `remote` ('same standard support as other tools') and implies `session_id` via the pty continuation flow, but says nothing about `cwd`, `harness`, or the action enum nuances beyond restating start/status/cancel. Baseline 3 for a 50%-covered 6-param tool.

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 set (開始・確認・取消 = start/status/cancel) tied to a specific resource (各harnessの公式CLI認証), and explicitly separates itself from agent_launch by noting that 'authenticated' is not launch readiness. An agent can identify the tool's scope without opening the schema.

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 concrete workflow routing: for 'waiting' show the URL/code to the human, and for 'input_required' feed the official screen via pty_send/pty_key in the same session. It also names the distinguishing boundary with agent_launch. It does not state when NOT to use the tool (e.g. if already authenticated), so it stops short of full when/when-not coverage.

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