Mark email

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

Annotations already declare idempotentHint=true, so the 'idempotent' sentence largely restates structured data; the concrete example ('already-read → no-op') adds modest clarity about semantics. It says nothing beyond that: no auth/permission needs, no disclosure of whether the change is reversible, and no note on side effects for other clients or integrations.

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 short sentences, purpose first, behavioral caveat second; no filler and nothing that doesn't earn its place.

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 simple four-parameter flag-mutation tool with a fully documented schema, the description covers purpose and idempotency adequately. It omits any mention of the response/result (no output schema exists) and any permission context, which is a minor but real gap.

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%, with the action enum documented as 'read, unread, flag (star), or unflag (unstar)'. The description merely repeats the same action vocabulary without adding format, constraints, or interaction details, 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?

States a specific verb ('change email flags') and enumerates the exact resource operations (read/unread, flag/unflag), so an agent immediately knows what it does. It implicitly distinguishes itself from siblings like move_email, delete_email, and add_label, but never names or contrasts an alternative explicitly.

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 action list implies what the tool is for, and the idempotency note hints at safe re-invocation. However, there is no guidance on when to use this vs add_label/remove_label (labels) or move_email, nor any stated permissions or prerequisites, leaving routing to inference.

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