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

Annotations declare non-readOnly, non-idempotent, non-destructive. The description adds genuinely useful behavior beyond that: untouched labels are preserved, and the change does not propagate to future replies. It does not disclose auth/permission needs or what happens when a remove_labels entry isn't present, so it stops short of full transparency.

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 tight sentences with no filler. The scope and mutation direction are front-loaded, and the side-effect caveats follow immediately after.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. The description covers scope and non-inheritance well, but for a mutation tool with 0% schema coverage it could say more about permissions, unknown-label handling, and the thread_id parameter.

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 0% at the parameter level, so the description carries the burden. It maps to add_labels/remove_labels by saying 'add or remove labels', but thread_id is never mentioned and no format, limits, or case-sensitivity guidance appears in the description. Baseline 3 for a partially compensating description.

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 pair (add/remove) plus the resource and exact scope: labels on all current received and sent messages in a conversation. This cleanly separates it from siblings update_message_labels, update_sent_message_labels, and bulk_update_* which operate on other scopes.

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 scope statement ('across all current received and sent messages in a conversation') implicitly tells the agent when to pick this over the message-level or sent-only label tools. It also sets the boundary that future replies are not affected, but it never names an alternative tool or states an explicit when-not condition.

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