auth

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

Annotations are non-contradictory. Description adds significant context: auto-refresh of token with ~90-day window, persistence to ~/.outlook-assistant-tokens.json, and diagnostic info for action=about. No hidden behaviors.

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?

Single paragraph covering all aspects, but slightly lengthy. Could be organized with bullet points for actions, but every sentence is essential and well-placed.

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?

No output schema, but description covers return/behavior for each action: status returns auth state, authenticate returns code/URL, about returns diagnostics. Also explains token persistence across restarts, fulfilling all needed context.

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 100%, but description enriches each parameter with context: action enum behaviors, method workflow details, force flag usage. Goes beyond enum values to explain real-world implications.

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?

Clearly states it manages authentication for Microsoft Graph API, with specific actions (status, authenticate, device-code-complete, about). Differentiates from sibling tools by being a utility for auth, while siblings handle email/event operations.

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 advises calling action=status first to check auth state before other tools. Details when to use each action and method (device-code for headless, browser for local server). Provides clear ordering and prerequisites.

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