label_message

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety is covered. The description then adds genuinely non-derivable behavior: moving a message to a folder changes its id and the new id is returned, and a message can hold only one folder label at a time. It stops short of stating failure behavior for invalid label ids or permission requirements.

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, front-loaded with the action, then the label vocabulary, then the one side effect that matters. No filler, nothing repeated from structured fields except where it aids scanning.

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 two-parameter mutation with no output schema, the description covers the important gap (the id-changing side effect and the returned value) plus folder semantics. Missing only edge-case behavior: what happens with an invalid label id, and how folder replacement interacts with the existing INBOX label.

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?

Only 50% of the schema is documented: `labelIds` carries a rich enum-like description in the schema (and the description redundantly restates parts of it), while `messageId` has no description anywhere. The description partly compensates by implying the id may change and be re-issued, but the primary identifier's semantics remain undocumented.

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 and resource ("Adds labels to a message") and enumerates what each label class does (STARRED, UNREAD, folder label). However, it never distinguishes itself from the near-identical sibling `update_message_labels`, nor from `label_thread`, leaving real ambiguity about which add-labels tool to pick.

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?

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. With siblings `update_message_labels`, `unlabel_message`, and `label_thread` in the same namespace, the agent is left to infer whether this tool replaces, complements, or duplicates them.

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