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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds real context beyond them: it discloses that it returns a cached gallery URL rather than rendering anything, and that personalization requires a prepared catalogKey. Useful behavioral detail, though it doesn't cover failure modes or rate/caching 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?

Three sentences, front-loaded with the core action and return, then the mode distinction, then the negative scope. No wasted prose; each sentence carries distinct information.

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?

Output schema exists so return values needn't be explained, annotations cover safety, and the schema fully documents params. The description supplies the one thing structured fields can't: the decision logic between static discovery and personalized previews. Nothing essential 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%, so baseline is 3. The description goes beyond individual param docs by explaining the combined effect of projectId+catalogKey (personalized vs static) and referencing device and template subset selection, adding semantic meaning the schema fields document only in isolation.

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: it 'displays the cached screenshot-style picker and returns its gallery URL.' The 'screenshot-style' qualifier implicitly distinguishes it from browse_social_templates, but the sibling is never named, so an agent must infer the split rather than read it.

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?

Explains two modes: 'project plus prepared catalogKey enables personalized V1/V2 previews; without a catalog it provides static discovery,' and the closing sentence rules out generating options, applying a style, or creating a variant (routing away from apply_screenshot_style/create_variant). Clear usage context, though it never names the sibling alternatives explicitly.

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