login

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

Annotations only flag a non-read-only, open-world, non-destructive call; the description adds the important traits beyond that: a browser window and MFA interaction on the user's machine, tenant-default behavior ('organizations' = any work account) with the wrong-tenant risk, and that the app choice is persisted and cannot be changed from chat. It omits what a successful return looks like and what happens on failure/timeout.

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, then a numbered decision list for the app choice, then small notes on timezone and persistence. It is somewhat long, but nearly every line carries actionable setup detail rather than 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?

Given four optional parameters, no output schema, and an interactive auth flow, the description covers the decision space, defaults, and post-configuration constraints well. What is missing is the relationship to auto_login/auth_status and any statement of what the call returns or how long it blocks.

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%, so the description must carry the load, and it does: client_id is a GUID required for app='own', tenant is a tenant ID or verified domain (optional for 'microsoft', default 'organizations'), and timezone accepts 'auto' or an IANA zone with a documented default. Every one of the four parameters is given meaning the schema alone does not provide.

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 ('Sign in to Microsoft 365') plus the mechanism ('Opens the system browser on this computer for sign-in/MFA'). It is clearly distinct from the planner/todo tools, but it never names its closest siblings (auto_login, auth_status), so an agent must infer the split between interactive and automatic sign-in.

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 instructs to ASK THE USER which app to use on first use or when switching, enumerates both options with their prerequisites, and says to omit app to reuse the saved choice. It also documents the escape hatch (terminal command / extension settings) for changing the app later, but does not say when to prefer auto_login or auth_status instead.

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