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

Goes well beyond the annotations (destructiveHint/readOnlyHint/idempotentHint) by disclosing concrete consequences: mail stops, the mailbox's stored mail is deleted, the main inbox is untouched, confirm gates the mutation, an account token is required, and 'Does not charge' addresses cost.

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?

Short, front-loaded fragments with zero filler; the critical consequences and the confirm gate come first, and every sentence carries information.

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 destructive, no-output-schema tool, the description plus annotations give an agent what it needs: scope, consequences, dry-run behavior, and auth/cost notes. Minor gaps remain around error conditions (e.g., nonexistent address) but nothing critical.

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 site/address/confirm are already documented in the schema. The description's 'confirm=true applies it' largely restates the schema's confirm description, adding little new semantic detail; baseline 3 is appropriate.

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+scope: 'Removes one email address from a site's domain.' It also carves out what it is not ('The main inbox is not removed here'), distinguishing it from siblings like rename_main_inbox and turn_off_email.

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?

Gives clear context for use: it removes a single address, mail to it stops, the main inbox is excluded, and confirm=true actually applies the change. It stops short of naming an explicit alternative tool for full-account email shutdown, but the exclusion rule is stated.

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