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

Annotations already flag destructive=true and idempotent=true, but the description goes well beyond them: it enumerates exactly what is erased (letters, their timeline rows, mail marks, an emptied conversation), notes the response reports the amount erased, and states the connected-mailbox refusal case and authorization requirement. This is the substantive behavioral context annotations cannot carry.

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?

Front-loaded with the core action, and every clause carries information. The em-dash enumeration of erased artifacts makes the second sentence long and slightly dense, but nothing is redundant filler.

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 single-parameter destructive mutation with no output schema, the description covers the action, side effects, refusal case, permission requirement, and even the return value ('the answer says how much'). Nothing an agent needs to call it correctly is missing.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds semantics the schema lacks: it accepts an address (jane@investor.com) or a domain (investor.com), and explicitly notes that a domain entry also covers its subdomains. That subdomain scoping is real added meaning.

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?

Names a specific verb (add an address/domain) and a specific resource (the mail Tommo won't read), and clearly delineates scope: address entries and domain entries including subdomains. An agent can distinguish this from remove_from_the_mail_tommo_wont_read and read_the_mail_tommo_wont_read at a glance.

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 the operative context ('From then on no letter... is fetched, read or kept'), a prerequisite ('For a signed-in admin or owner'), and an explicit refusal condition ('Refused for an entry that covers a connected mailbox itself'). It does not name sibling alternatives such as block_a_sender or remove_from_the_mail_tommo_wont_read, so it stops short of full when-not guidance.

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