create_label

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, but the description adds concrete meaning: an existing label is returned unchanged rather than erroring, and system labels (INBOX, SPAM, TRASH) are actively refused. Those refusal and no-op behaviors are not derivable from the annotations and prevent surprise failure paths.

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?

The core action and its two edge-case behaviors are front-loaded in three compact sentences, followed by a terse per-argument list. The only flaw is the mid-sentence line break ('returned\nas it is') that slightly impedes reading, but there is no wasted content.

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 tool with annotations covering the safety profile, the description covers creation semantics, idempotency, and refusals. Since no output schema exists, it could say more about the returned label object (id, name) on success, but the 'returned as it is' phrasing covers the critical case.

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%, so the description fully carries the burden and does so for both parameters: it explains that '/' in displayName separates nested labels and that autoCreateParentLabels defaults to true. Minor remaining gap is that displayName has no stated length or character constraints.

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 ('Create a user label') and immediately disambiguates it from the sibling label-application tools (label_message, label_thread) by clarifying that this creates the label itself, not an association. The 'Projects/2026' example makes the nesting semantics concrete and unambiguous.

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?

Usage is implied rather than stated: the agent learns that existing labels produce a no-op and that system labels are refused, which frames when to call it. However, there is no explicit routing to alternatives (e.g., 'to apply an existing label, use label_message instead') and no prerequisites such as required auth scopes.

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