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

Annotations only declare readOnlyHint=true and openWorldHint=false, yet the description adds substantial behavioral context the agent could not otherwise know: the per_second billing RATE semantics, the real_person_verification auto-verification step for Seedance 2.0, and plan-based requires_upgrade annotation of recommended rows.

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?

Dense but well front-loaded: the model list and row-shape fields come first, followed by the critical cost warning and per-action semantics. The CAPS emphasis (HEED, NEVER) is loud but functional for an agent; length is justified by real payload, though a browse tool carries more prose than strictly necessary.

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?

With no output schema, the description carries the full burden of explaining return values and does so thoroughly — reference_limits, modes, credit_cost_unit, per-model reference-input envelopes, and plan annotations. Nothing an agent needs to call or interpret this tool correctly 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 the baseline is 3, but the description adds meaning beyond the schema — how type and query combine for filtering, what action:'get' returns (input modalities, aspect ratios, reference envelope), and the practical 'prefer rows without requires_upgrade' guidance.

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 opens with a specific verb+resource ('Browse Popcraft AI models') and immediately names the concrete catalog contents (GPT Image 2, Seedream, Nano Banana, etc.). It is unmistakably the catalog-browsing tool, clearly separable from the generate_* and show_* siblings.

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?

It gives explicit when-to-use routing: 'Consult these BEFORE attaching medias', 'Unsure which model to use? Call recommend first', and the critical directive to call the matching generate tool with get_cost:true rather than quoting creditCost. Alternatives and preconditions are named, not implied.

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