logout

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation risk is covered by structured data. The description adds genuinely useful scoping ('locally stored'), implying server-side sessions may persist and that subsequent calls will need re-authentication, but it stops short of stating that consequence explicitly or whether the destruction is reversible.

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?

One short sentence, front-loaded with the action and qualified by the most important constraint. Nothing is wasted and nothing is buried later in the text.

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, no-output-schema tool whose safety profile is already carried by annotations, the description covers what is needed to call it correctly. The only meaningful omission is the practical consequence of calling it, namely that the agent will need to run login again before further MyChart calls.

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 clarify and the baseline of 4 applies. The single constraint that matters — that no identifier is needed because the target is implied local state — is effectively conveyed by 'locally stored'.

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 ('Delete the ... MyChart tokens') and narrows scope with 'locally stored', which tells an agent this is a client-side credential wipe rather than a server-side session revocation. It is clear on its own, though it does not name or contrast itself with siblings like login or login_status.

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?

The intent of a logout tool is strongly implied by the name and the delete-tokens phrasing, so an agent can infer it is the terminal step after using the session. However, there is no explicit statement of when to call it, whether it is required before switching accounts, or what happens to the existing session afterward.

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