auth_login

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

Adds substantial behavior beyond the annotations: the call returns immediately with a consent URL rather than blocking, consent must be granted on the same machine (loopback 127.0.0.1 constraint), and the refresh token is persisted in the OS config dir with 0600 permissions. This is exactly the auth-sensitive context an agent cannot get from openWorldHint alone, and it does not conflict with the 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?

Four short, front-loaded sentences that each carry distinct load: mechanism, return behavior, next step, and side effect. No restatement of the tool name or 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 one-parameter flow tool with no output schema, the description covers what is returned (consent URL), what the agent should do next (poll auth_status), and where credentials land. The only omission is any explanation of timeoutSeconds, which is the sole remaining hole.

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 0% and the single parameter timeoutSeconds is never mentioned in the description, so its units, default, or effect are undocumented anywhere. The description compensates richly on behavior but not on parameters, leaving a genuine gap for the one input an agent must supply.

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 (one-time Google OAuth login via loopback on 127.0.0.1) and its immediate effect (returns a consent URL). It also differentiates from siblings by naming auth_status as the polling counterpart, so an agent can route between them without opening a 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 clear operating context: 'one-time', 'the owner opens it in a browser on THIS machine', and 'Poll auth_status until ready'. The 'one-time' qualifier implies this should not be re-run routinely, but there is no explicit when-not guidance or statement of prerequisites/failure handling.

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