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

Annotations already indicate destructiveHint=true, and the description adds concrete detail: confirm revokes all old tokens, emails a short-lived code, and returns fresh tokens. It also discloses no authentication required and rate limiting per IP/site, going beyond the structured 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?

The description is compact, with purpose front-loaded in the first sentence and actionable details following. It uses three sentences to convey actions, prerequisites, and limitations without redundant wording.

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 there is no output schema, the description covers return values (fresh application/API token) and the side effects (revoking old tokens). It also includes rate limits and authentication requirements, making it complete for the tool's complexity.

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% with parameter descriptions, but the description enriches meaning by explaining the workflow: action=start emails a code, action=confirm with code verifies and returns tokens. It also ties site_url to the apply registration, adding context not in 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 clearly states the tool recovers account access when tokens are lost, and enumerates the two actions (start/confirm) with their specific purposes. It distinguishes itself from sibling tools like apply by referencing the registration prerequisite. This is a specific verb+resource with clear scope.

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 gives clear usage context: when application/API tokens are lost, use action=start then action=confirm. It also notes that site_url must have been previously registered with apply, providing a prerequisite. However, it does not explicitly compare with alternative tools like reclaim or state when not to use, so it stops short of full exclusion guidance.

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