update_label

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

Annotations already declare this is a non-destructive mutation, so the bar is lower. The description still adds real value beyond them: partial-update semantics ("Only the fields you pass change") and the non-obvious side effect that a "Parent/Child" new_name relocates the label in the hierarchy rather than just renaming it. It does not cover permission requirements, whether existing filters referencing the renamed label are affected, or error behavior.

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 sentences, front-loaded with the operation and its modes; the second sentence carries the constraints. The palette enumeration is long but every hex value prevents a failed call, so it earns its space. Slight overhead from listing colors inline.

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 7-parameter mutation with no output schema and clear annotations, the description covers mode, partial-update semantics, nesting behavior, and the color constraint. Remaining gaps are around failure modes and downstream effects on filters/rules, which are secondary for correct invocation.

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 coverage is 86%, so the schema already carries most parameter meaning and the baseline is 3. The description fills the notable gaps the schema leaves: it supplies the concrete Gmail palette values for background/text (the schema only says "Hex color from the Gmail palette") and explains the "Parent/Child" convention for new_name, which the schema leaves completely 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?

The description opens with a specific verb+resource ("Changes a label") and enumerates the three changeable facets: rename/move, recolor, and visibility. That distinguishes it from create_label and list_labels without naming them, but a one-line contrast with create_label would have made it a 5.

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 by the enumeration of editable facets, and "Only the fields you pass change" tells the agent partial updates are safe, which nudges toward preferring this over delete/recreate. It never states when not to use it, nor prerequisites such as whether the label must already exist.

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