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

Annotations already declare readOnlyHint and openWorldHint, so the description's added context is the real contribution: a credit cost (10 credits) and a precise inventory of returned fields, including the platform caveat that transcripts only apply to Meta. It does not cover failure modes for malformed or unsupported links.

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?

Two sentences, no filler: the return payload leads and the practical use plus cost follow. The parenthetical platform-URL block is long but each entry is load-bearing for input format.

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 burden of describing return contents and does so field by field, adds per-platform coverage and a cost signal, and gives input format examples. An agent has everything needed to decide to call it and construct the argument.

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 schema already defines the single url parameter and the Meta ad ID alternative. The description adds value by supplying recognized link formats for Meta, Google, LinkedIn, and TikTok, which tells the agent what a valid input string actually looks like.

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?

Names a specific verb (read) and resource (an ad's full creative) and enumerates exactly what is returned: every version, CTA, destination, days running, and the Meta video transcript. The requirement of an ad-library link implicitly separates it from search_ads/advertiser_ads, but no sibling is named explicitly.

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?

'Use it to break down the hook, script and offer' gives a concrete use case and implies the tool is downstream of a discovery step, since it needs a library URL. It stops short of stating when not to use it or naming search_ads as the way to obtain that URL.

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