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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds little beyond that—it only mentions search filtering and the output format 'lean TOON text,' which is vague and unexplained. No additional context about output structure, pagination, or latencies is provided. This does not contradict annotations, but adds minimal behavioral value.

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?

The description is a single, compact sentence that gets straight to the point. It contains no filler, is front-loaded, and communicates the essential information efficiently. It is appropriately concise for a simple listing tool.

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?

Given the tool's simplicity (0 required params, no output schema, annotations covering safety), the description is mostly adequate. However, it leaves `onlyRecommended` unexplained, and the term 'TOON text' is ambiguous without further context. The description could be more complete by detailing what the output looks like or what 'lean TOON text' means, but for basic invocation, it may suffice.

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?

The schema has 0% description coverage, so the description must compensate. It clarifies the `search` parameter by stating it filters by name, slug, description, or tags, adding real semantic value. However, `onlyRecommended` is not explained at all—its meaning is only inferable from the name. This partial explanation is helpful but incomplete.

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 description clearly states the tool lists TTI (text-to-image) models, using a specific verb and resource. The name itself is explicit about the domain (images) and action (list), and it distinguishes from sibling tools like magnific_video_models_list and magnific_audio_voices_list. The only minor ambiguity is the phrase 'lean TOON text,' but it doesn't obscure the core purpose.

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?

The description provides no explicit guidance on when to use this tool over alternatives. It implies you use it to list TTI models, but there are no exclusions or alternative references. The sibling context shows many similar list tools, so some guidance would help, but the name and purpose are clear enough for basic selection.

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