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

Annotations cover safety hints, but the description adds substantial cost and lifecycle context they cannot express: 4 credits per set regardless of template count, credits charged from the account, automatic refund on a failed set, and 3 render sizes per template. It also states the queuing/async nature and points to the polling tool, so the agent knows the result is not immediate.

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?

Purpose and cost are front-loaded and every sentence carries operational information; nothing is padding. The inline parenthetical catalogue of six templates is dense and slightly harder to scan than a list, but the information is not redundant.

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?

There is no output schema, but the description tells the agent results arrive asynchronously and must be fetched via list_static_ads, and covers cost, refund behavior, render sizes, and template defaults. Nothing an agent needs to invoke this 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 baseline is 3, and the description goes further by defining what each of the six template ids actually produces (e.g. 'us_vs_them — a side-by-side comparison, never names a competitor'), which the enum alone does not convey. product_id is only glossed as 'one catalog product' — the schema's 'from list_products' carries that weight.

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 — 'Queue a set of static ad images (Meta, TikTok) for one catalog product' — with the key qualifier that it builds from the product's own photos. An agent can distinguish it from create_image, generate_photos, and generate_carousel from the first clause alone.

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 operating context: one catalog product, optional template subset, 'Leave templates out to get all 6 of them', and the follow-up step 'Poll list_static_ads for download links'. It stops short of naming an alternative tool (e.g. generate_carousel or generate_photos) and when that would be preferred.

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