Start signing in to Microsoft 365

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

Annotations already declare readOnlyHint/idempotentHint, but the description adds substantial behavior beyond them: the browser opens locally, the tool returns immediately, repeat calls reuse a pending attempt rather than spawning another window, consent is incremental, and no token is ever returned. It even adds a safety directive (never ask the user to paste credentials or an authorization code).

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 mechanism before routing guidance, and most sentences carry distinct information. It is on the long side, with the incremental-consent point restated in both the description and the `scopes` guidance, but no sentence is 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?

No output schema exists, yet the description covers the async result path by pointing to auth_login_status, explicitly states no token is returned, and explains the consent scope semantics for both parameters. An agent has everything needed to invoke it correctly.

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%, so the baseline is 3, but the description adds semantic framing beyond the schema: a bare call asks only for the minimal set, each repeat consents to just what was added, and `full` avoids consenting to admin-only/tenant-blocked scopes. This goes slightly beyond the schema text even though the two overlap on the `scopes` guidance.

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?

Names a specific verb and resource (starts OAuth 2.0 browser sign-in to Microsoft 365 using authorization code + PKCE) and distinguishes itself from the sibling auth_login_status by explaining that it returns immediately while the status tool reports completion. An agent can tell it apart from session_status and graph_request without opening schemas.

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 states when to call it (a tool reports no session), when to call again with `scopes` (a tool reports missing consent), the incremental nature of consent, and what `mode: "full"` does instead. It also names the follow-up tool auth_login_status and the alternative of a bare call for minimal consent. Nothing is left to inference.

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