auth

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

The description adds significant behavioral context beyond the minimal annotations: auto-refresh of expired access tokens within a ~90-day window, token persistence to a specific file across restarts, the need to run a local server for browser auth, and the effect of `force: true` on an existing session. There is no contradiction with the annotations (readOnlyHint=false, destructiveHint=false).

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?

The description is long but every sentence earns its place, covering all four actions, defaults, prerequisites, and persistence in a compact, logically ordered paragraph. It uses semicolons and clauses to group related information, making it dense but not wasteful.

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 multi-action auth tool with no output schema, the description is remarkably complete. It describes what each action returns or does, prerequisites (npm run auth-server), failure/success flow (device-code-complete after browser entry), and persistence behavior. The agent has enough context to use the tool correctly without external documentation.

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?

Although schema coverage is 100%, the description enhances the schema by stating defaults (`action=status`, `method=device-code`), explaining the behavior tied to `force`, and describing the distinct outcomes of each `action` value. It also clarifies the meaning of `method` options (headless vs. local server), adding value beyond raw parameter names.

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 clearly states the tool's purpose: 'Manage authentication with the Microsoft Graph API' and enumerates the four specific actions (status, authenticate, device-code-complete, about). It is easily distinguishable from the sibling email/calendar tools, and the action list gives a precise map of what the tool accomplishes.

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?

Explicitly tells the agent when to use this tool: 'call this first to check before other tools.' It also gives conditional guidance for each action—e.g., use device-code for headless environments, run `npm run auth-server` before using the browser method, and call device-code-complete after the user enters the code. This is strong, actionable usage context.

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