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

Annotations declare destructiveHint=true, but the description adds critical context annotations cannot: Local MCP holds no OneDrive sign-in, nothing is actually signed out, the sync app stays signed in, and the effect is only that tools stop reading the folder. It also discloses the reversibility gap by naming the UI recovery path. This is exactly the value-add behavioral context the annotation cannot convey.

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 core action, then layers in the crucial non-obvious details (no sign-out, irreversible from the tool side). Sentences are dense but each earns its place. The UI re-enable path is somewhat verbose but practical.

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 the tool has an output schema and full schema coverage, the description fills the most important gaps: what actually changes, what doesn't, and how to recover. It's complete enough for an agent to call correctly. Minor omission: `confirm` parameter behavior is left to the schema.

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 both parameters are documented. The description restates the `account` semantics (name from onedrive_root, required when multiple folders) but adds nothing beyond the schema. It doesn't mention `confirm` at all, though the schema flags it as ignored. Baseline 3 is appropriate given full schema coverage.

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+resource: turning one OneDrive folder off in Local MCP. It also clarifies what it is NOT (not signing out of OneDrive or the sync app), which distinguishes it from a generic 'disconnect' an agent might expect. It doesn't explicitly name disconnect_m365_account or gdrive_disconnect as alternatives, but the scoping to a single synced folder is clear.

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?

Explains the required context: `account` can be omitted with one folder but must be given with several. It also tells the agent the action is irreversible from the tool side ('No tool turns it back on') and directs the user to the UI path to re-enable. It does not explicitly compare against sibling disconnect tools, but the functional scope is clear.

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