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

Annotations already flag destructiveHint=true, but the description goes further and discloses exactly what is destroyed (everything of theirs waiting in External), that the effect is workspace-scoped, and critically that the deletion is irreversible ('the deleted emails do not come back') while the block itself is reversible via unblock_sender. That asymmetry is the key behavioral fact an agent needs before invoking.

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?

Two sentences, no filler, with the destructive scope front-loaded and the reversibility caveat following immediately. Every clause carries non-redundant 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 single-parameter destructive tool with no output schema, the description covers scope of destruction, irreversibility, and the recovery path. There is no undeclared behavior an agent would need in order to call it correctly.

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?

There is only one parameter (emailId) and its schema description already points to list_external_mail at 100% coverage, so the description adds no parameter-level meaning. Baseline 3 is appropriate when the schema fully carries the parameter documentation.

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 states a precise compound action — block the sender workspace-wide and delete all of their pending External mail — which is more than the name 'mark as spam' conveys on its own. It explicitly names the sibling that reverses it (unblock_sender), so an agent can distinguish it from delete_external_mail without opening schemas.

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?

It gives clear context (spam from an External sender, workspace-scoped) and points to unblock_sender as the inverse operation. It does not, however, explicitly exclude the adjacent delete_external_mail tool that removes a message without blocking the sender, so the when-not case is left to inference.

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