Make a video ad from a product link

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

Annotations only declare non-read-only, non-idempotent, open-world, non-destructive; the description adds side effects the annotations cannot express — the product is saved to the brand's catalog and the page photo is pinned to this ad while the brand's default photo is not changed. It also discloses fallback behavior for server-blocked pages (real browser, then name from link plus searched photo) and that the reply reports which path was taken.

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-loaded with the core action and the render hand-off follows immediately; nearly every clause carries new information (scope, side effects, fallbacks, next call). It is a single dense paragraph with stacked parentheticals, so it could be split for scanability, but there is little true waste.

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 5-parameter, non-read-only, open-world tool with no output schema, it covers the four things an agent actually needs: what gets saved vs. left alone, what the reply looks like under degraded reads, that no video is produced here, and the exact follow-up call with dryRun for pricing.

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% and the style enum is fully self-documented, so the baseline is 3. The description mentions only the URL input ('Paste a product page link') and adds nothing about say, style, language, or durationSeconds beyond what the schema already says.

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 chain and resource: takes a product page link and produces a planned creator-style video ad, including the page-reading and catalog-save steps. It is clearly separable from render_ad (explicitly) and from plan_ad/product_sizzle by scope, so an agent can distinguish siblings without opening schemas.

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?

Explicitly says 'Nothing renders here: show the user the concept, then call render_ad with the returned creative (dryRun:true first for the exact price)' — a concrete when-to-use-this-vs-next-tool routing rule. It also states the precondition that it works with or without a saved brand, removing the main ambiguity about required setup.

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