gmail_trash

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

With no annotations provided, the description carries the full burden and does disclose the key traits: the operation is non-destructive in practice (Trash), reversible via gmail.restore/gmail.undo, and gated by confirm=true. What it omits is batch behavior — whether a bare call with no selector targets everything — which matters given the `all` parameter.

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 waste, and the most important fact — this is a Trash move, not a permanent delete — is front-loaded in the parenthetical before the precondition.

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-category tool with no annotations and no output schema, the description covers reversibility and the confirm gate, which are the two things an agent most needs. It leaves the selection-mode interaction (`all` vs `index`/`indexes`/`match`) entirely to the schema, which is acceptable at 100% coverage.

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 description coverage is 100% across all 8 parameters, so the schema already explains `all`, `index`, `match`, `query`, `folder`, `indexes`, and `max_rows`. The description's only parameter-level contribution is restating the confirm requirement, so the baseline of 3 applies.

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?

"Delete conversations (move them to the Trash)" gives a specific verb plus resource and immediately disambiguates the kind of delete — soft/trash, not permanent. It does not name gmail_delete_forever as the sibling for irreversible removal, but naming gmail_restore/gmail_undo establishes the reversibility boundary.

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 states a hard precondition ("Requires confirm=true"), which is genuinely useful invocation guidance. However, it never says when to choose this over gmail_archive, gmail_spam, or gmail_delete_forever — the selection logic is only implied by "move them to the Trash."

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