Manage Gmail Label

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

Annotations already establish readOnlyHint=false and destructiveHint=true, and the description's 'delete' action is consistent with that safety profile — no contradiction exists. The description adds only concrete outcomes (create/update/delete) but no nuance such as system labels being undeletable, whether update is partial or full replacement, or failure behavior. Since annotations carry the safety load, the description contributes minimal additional behavioral context beyond what is already structured.

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?

A single 10-word sentence, front-loaded with the verb+resource pair and followed by a colon-enumerated operation list. Every word contributes, with only a trivial repetition of 'labels' in the enumeration. It is highly scannable in a sibling list of over 130 tools.

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?

Moderate complexity — 6 parameters, 3 operation modes with distinct parameter requirements, and destructive potential — is substantially covered by the 100%-coverage schema, the presence of an output schema, and the safety annotations. What remains for the description is selection guidance and behavioral nuance, which is thin: no sibling routing and no disclosure of edge cases like system-label restrictions. This is adequate as a minimum viable definition but leaves clear gaps.

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%, and the schema itself documents conditional requirements ('Label name. Required for create, optional for update' and 'Label ID. Required for update and delete operations') as well as enum defaults for the visibility parameters. The description adds no parameter-level meaning beyond restating the action enum already present in the schema. The baseline of 3 applies because the schema does the heavy lifting.

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?

The description identifies the resource (Gmail labels) and enumerates the full operation set ('create, update, or delete'), making the tool's scope unambiguous. The action set implicitly separates it from read-only sibling list_gmail_labels and from modify_gmail_message_labels, which operates on message-label assignments rather than label definitions. However, it never explicitly names exclusions or sibling alternatives, so differentiation is inferred rather than stated.

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 operation set implies the tool's use cases — creating, updating, or deleting label definitions — giving an agent a reasonable heuristic for selection. The description provides no explicit when-to-use guidance, no exclusions, and does not route the agent to list_gmail_labels for read-only viewing or to modify_gmail_message_labels for attaching labels to messages. This is implied usage at best, with no alternatives or conditionals stated.

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