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

Annotations carry only destructiveHint=true; the description adds the crucial partial-update semantics ('only modifies the fields you specify — all other data is preserved') and details the write-tier approval flow including the distinction between from-now-on vs just-once approvals and the instruction not to re-ask in chat. This materially enriches the bare annotation. No contradiction with annotations.

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?

Well front-loaded: verb+scope first, then use cases, routing, and prerequisite. The approval-flow paragraph is slightly verbose but each clause conveys distinct, non-redundant operational guidance. A touch long, but nothing is filler.

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 nested-object, mutation tool with no output schema, the description covers everything an agent needs: what fields update, what is preserved, when to call it, when to use the alternative, the prerequisite read, and the approval protocol. Nothing required for correct invocation is missing.

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 100% and the schema already documents both parameters richly, including nested merge-by-key behavior for colors and typography. The description reinforces this ('Only the fields to update; others are preserved') but does not add material meaning beyond the schema. Baseline 3 is appropriate when the schema carries the weight.

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 ('Update'), resource ('brand guidelines'), and the exact fields covered (visual identity, naming, positioning). It also names the sibling it is not — update_voice_profile — for the writing/voice domain. An agent can tell this tool apart from its siblings without opening the schema.

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?

Explicitly lists when to use (colors, tagline, typography, personality/tone, naming rules, visual dos/donts), when NOT to use (voice/cadence → update_voice_profile), and a mandatory prerequisite (call get_brand_guidelines first). This is textbook when/when-not/alternatives guidance.

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