Read or save the brand kit

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description only needs to add context. It does add two real facts: the call costs nothing ("Free.") and passing an empty object for voice clears the stored voice. It omits what "save the user's confirmed one" implies about overwriting existing values and gives no sense of what the read path returns.

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?

It is short, but shortness here is compression rather than clarity: sentence fragments, an ambiguous leading "Free.", and a colon-based shorthand that forces re-parsing. The read behavior and the write behavior are interleaved instead of front-loaded as two clear modes.

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 dual-mode tool with two nested-object parameters, no output schema, and no required fields, the description is far too thin. An agent cannot tell what the read path returns, whether a partial save overwrites untouched fields, or how this relates to extract_brand and the actor/voice listing tools.

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 50%: the design parameter has a description, but voice is a bare object with no schema documentation. The description partially compensates by defining the voice reset idiom ("voice {}" clears it) and framing both params as accepting the user's confirmed values, yet it never says what shape either nested object takes or whether they can be passed independently.

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 fragments "saved design, script voice, our looks and faces" plus "design, voice: save the user's confirmed one" do convey a dual read/save purpose for the brand kit, but the phrasing is telegraphic and "our looks and faces" is never unpacked. Nothing distinguishes this from siblings such as extract_brand, list_voices, or get_actor_defaults, so an agent must guess which tool owns brand-kit state.

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?

"Alone:" hints that calling with no arguments performs the read, and the "design, voice:" clause hints at the save path, so a mode distinction exists in spirit. But it is never stated as a rule, there are no exclusions or alternatives named against extract_brand/list_voices, and "Free." is an unexplained cost note rather than usage guidance.

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