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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety bar is lower. The description still adds real value: it scopes the destruction to local state ("Forget the app's secret and the mailboxes") and explicitly says "Nothing in Microsoft 365 changes," resolving the ambiguity that destructiveHint=true would otherwise create about remote data. "Free" adds a cost signal not present in 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?

Three very short sentences with the primary effect front-loaded and the key reassurance ("Nothing in Microsoft 365 changes") second. "Free" is slightly stray but does carry information about cost.

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 zero-parameter disconnect tool with annotations covering the safety profile and no output schema, the description covers what is removed, what is not affected, and that there is no charge. It omits what an agent should do afterwards (reconnect via m365_connect, downstream mail/file calls failing), which is a minor gap.

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?

Zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description does not waste words on parameters, which is appropriate.

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?

"Forget the app's secret and the mailboxes" conveys that stored credentials and mailbox connections are removed, but it is metaphorical rather than a specific verb+resource statement, and it never says "disconnect" or "credentials" outright. It also gives no signal distinguishing it from the many other *_disconnect siblings (google_disconnect, salesforce_disconnect, hubspot_disconnect).

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?

There is no explicit when-to-use statement, no prerequisites, and no mention of alternatives or consequences of calling it (e.g. that mail/files tools will stop working until reconnecting). The usage context is only inferable from the tool name.

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