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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real context beyond that: the picker is 'cached', results are a URL plus format specs, and the never-generate/apply/create clause reinforces the boundary for an agent tempted to treat this as a generator. No permission or pagination notes, but the read-only surface is well clarified.

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?

Three sentences, front-loaded with what it returns, then the mode split, then the negative boundary. No filler. 'V1/V2 previews' is mildly opaque jargon, a small deduction but the structure is efficient.

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 need no explanation, annotations cover safety, and the schema fully documents parameters. The description's job reduces to explaining the two invocation modes, which it does. Slight gap in not stating what happens with a stale or expired catalogKey, but otherwise complete for a read-only browser.

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%, so all seven parameters including the projectId/generationId aliasing and the catalogKey pairing are already documented. The description adds only the semantic outcome of combining project + catalogKey (personalized vs. static), which the schema itself largely states. Baseline 3 is appropriate when the schema carries the parameter burden.

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 and resource (displays the cached social-style picker) and what it returns (gallery URL and format specifications). It distinguishes its two modes (personalized preview with project+catalogKey vs. static discovery) but never names the sibling browse_templates or apply_social_graphics_style it should be contrasted with, leaving sibling differentiation to inference.

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 an explicit condition for each mode: 'A project plus prepared catalogKey enables personalized V1/V2 previews; without a catalog it provides static discovery.' It also states what it never does (generates options, applies a style, creates a variant), which usefully excludes downstream actions. It stops short of naming which tool to use instead for those excluded actions, so no full alternatives map.

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