uoft_forget_session

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful specifics beyond that: exactly what is destroyed (local sessions and the encryption key) and for which scope (this MCP, both apps, not university-wide).

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?

Two short sentences, front-loaded with the destructive action and then the scope caveat. No filler, and the most important constraint is not buried at the end.

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-param, no-output-schema tool whose annotations carry the safety hints, the description is nearly complete, covering action and scope. The only unresolved ambiguity is what 'both apps' refers to and whether re-login is required afterward.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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 (cancel/delete) and resource (local sessions and encryption key), and explicitly scopes it away from a university-wide logout. An agent can distinguish this from uoft_login and uoft_auth_status without opening any schema.

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?

It gives clear context for use ('cancel login', local-only scope) and an explicit boundary ('not university-wide logout'), which tells the agent when this is inappropriate. It stops short of naming the alternative action (e.g. re-authenticating via uoft_login) after forgetting.

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