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

Annotations already declare read-only and idempotent, but the description still adds substantial behavior: newest-first ordering, the 30-day purge window, that a deleted folder or workspace counts as a single entry, the external-member filtering rule, and the FORBIDDEN condition on the account parameter. These are not restatements of the 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?

Length is proportionate to six parameters with non-obvious scoping rules, and the primary purpose plus ordering are front-loaded. It is slightly dense and semicolon-chained in the middle, but every clause carries actionable 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?

With an output schema present, return values needn't be explained, yet the description still tells the agent what columns to expect (deleted-at, deleted-by, purge-at). Combined with the scope matrix and permission caveats, an agent has everything needed to call it correctly on the first try.

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 the baseline is 3, but the description adds the default-scope semantics ('omit workspaceId, team and account for your own trash') and clarifies that type lists only a type the trash actually holds, which the enum description only partially implies. It stops short of covering limit/offset, which the schema already handles well.

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 opens with a specific verb and resource ('List what is in the trash') and immediately names the aspects it reports (deletion time, actor, purge date), which no sibling like trash_restore or trash_purge does. It is distinguishable from every other tool in the sibling list without opening the schema.

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 spells out the scope-selection decision tree explicitly: omit team/workspaceId/account for your own trash, pass team for team folders and workspaces, pass workspaceId for that workspace's items, and account only for platform admins (FORBIDDEN otherwise). It also points to trash_restore for the follow-up action, leaving nothing to inference.

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