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

Beyond the annotations, the description discloses the crucial side effect that the template 'goes live at once and replaces the always-on active template of the same placement', plus what the response returns (safe zones) and that Meta tags the variant per placement. This is exactly the kind of write-impact context annotations cannot convey. Minor tension with destructiveHint=false given the live replacement, though no outright contradiction.

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?

Front-loads the core action and keeps every sentence substantive, but the single dense paragraph with stacked parentheticals and ellipses is harder to scan than it needs to be. Slight trimming or splitting would improve it without losing 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?

For a non-idempotent, non-read-only tool with nine parameters and no output schema, the description covers the mutation's effect, the response contents, the body format, and the next step. It does not mention failure modes or validation/prerequisite checks (e.g., get_validation), which is the remaining gap.

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?

With schema coverage at 67%, the description still adds real meaning: the exact-ratio constraint for 4_5/9_16 canvases (1080×1350 / 1080×1920), the contents of the variable bag (product.rawData plus derived fields), and the non-obvious gotcha that sale_percentage already carries a '%' sign. Name, feedId, outputFormat, and backgroundColor are left to the schema, which documents them adequately.

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 ('Creates a NEW code-kind template on the feed') and immediately pins down the body language (Handlebars), distinguishing it from create_template_variant and update_code_template. The 'NEW' emphasis plus the replacement-of-active-template note makes the create semantics unmistakable.

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 clear conditional guidance for the placement parameter (default = main image, 4_5/9_16 = Meta aspect-ratio variant) and a mandatory follow-up ('After creation, call preview_render'), plus a routing pointer to list_handlebars_helpers. It stops short of stating when to prefer create_template_variant or update_code_template instead, so sibling selection is only partially covered.

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