Revoke a JWT session

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

Annotations already declare destructiveHint=true, so the tool is clearly destructive. However, the description adds valuable behavioral context beyond annotations: it clarifies the immediate effect ('whoever holds that session is signed out right away'), the required confirm flag, and the parallel to API key revocation. There is no contradiction with annotations, and the extra context is substantial.

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?

The description is two sentences long with zero filler. Every word adds value: the tool's effect, the required parameter, the severity comparison. It is front-loaded with the core action and then elaborates efficiently.

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's complexity (2 parameters, no output schema, destructive action), the description provides complete guidance: what it does, what it requires, what the outcome is, and how it compares to related actions. An agent can safely decide to invoke this tool with no additional documentation needed.

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 50% – the confirm parameter has a description, but jti does not. The description explicitly mentions that confirm is required, and that the effect is 'immediate' and 'same severity as revoking an API key', adding meaningful semantic context for the confirm parameter. While jti is not individually described, the description as a whole explains what the tool targets (a session), compensating somewhat. The baseline of 3 is elevated to 4 because the description adds clear value beyond the schema.

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?

The description uses immediate, specific verbs ('Immediately invalidate', 'revoke') with a clear resource ('one active browser/console session', 'interactive login'). It clearly distinguishes this from API key revocation by explicitly contrasting the type of credential being revoked, effectively differentiating it from sibling IAM revocation tools.

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 description explicitly states the tool requires 'confirm=true' and compares the severity to revoking an API key, providing clear context on when this is the appropriate tool (for interactive sessions) versus alternatives. The 'immediately invalidate ... same severity as revoking an API key' guides the agent to understand the weight of this action.

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