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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds the important scope constraint that only the active profile is affected. However, it never explains what 'destructive' means here — whether array fields are replaced wholesale or merged, and whether omitted fields are preserved — and given no required parameters this is exactly the ambiguity an agent needs resolved.

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 action and the mutable surface before the usage rationale. Dense but no filler; the only cost is that compressing the field list into one sentence makes the destructive/patch semantics invisible.

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?

An output schema exists so return values needn't be described, and annotations cover the safety profile. What is missing is the patch contract itself: with zero required parameters and additionalProperties=false, an agent still can't tell from the description whether a call containing only `bio` preserves the other fields, nor how to shape `audienceSize` in a nested-object schema.

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 0%, so the description must carry the load; it does name all seven field groups in prose, which is a real gain. But it adds no meaning about format, limits, or replacement semantics, and the nested `audienceSize` object (a map of non-negative integers) is only hinted at by 'audience-size estimates' — an agent cannot infer the key structure from either schema or description.

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 (patch) and a well-defined resource (the user's active brand profile), then enumerates the exact field groups that can be modified. An agent can map every description clause to the schema properties and knows no other brand-profile resource is touched.

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?

Gives concrete triggering context ('refine brand voice based on a transcript, style guide, or competitor analysis') and an explicit exclusion: only the active profile is mutated, so selection/creation must happen in the web app. No alternative tool is named, but none of the listed siblings overlaps, so nothing relevant is left ambiguous.

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