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

Annotations only declare readOnly/openWorld, so the description carries the real weight and does: pagination up to 20 pages of 100, a warning field when the search aborts early, a truncated object with result+warning instead of a list, the foreign_object error for cross-account IDs, and the status vs effective_status distinction. That is exactly the behavioral context annotations cannot supply.

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 one-line purpose, then per-parameter paragraphs, then a return-field block — easy to skim for an agent. It is long and the return-field enumeration partly duplicates the output schema, so a sentence or two could be trimmed, but almost every line carries operational meaning.

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?

An output schema exists, yet the description still adds the semantics an agent needs: lead_gen_form_id implies an Instant Form, link_url is a placeholder on lead ads, carousel/Advantage+ ads expose link_urls, and issues/review_feedback carry HARD_ERROR/SOFT_ERROR and global vs placement_specific feedback. Nothing needed for a correct call 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 0% with five parameters, so the description must compensate and it does fully: name_contains is server-side filtering, status filters on CONFIGURED status with documented pagination-until-limit behavior, limit has a default of 50 and a truncation contract, adset_id narrows scope, and workspace is optional with a single-workspace caveat.

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?

Opens with a specific verb+resource ('Meta-Ads auflisten, optional nur eines Adsets') and immediately clarifies the scope: status plus creative CONTENT, not just a reference. It also stakes a claim over a specific question ('wohin führt diese Anzeige?'), which separates it from the adset/campaign listers.

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 concrete routing advice: name_contains means one server-side call instead of listing everything and searching yourself, and it tells the agent to narrow via adset_id/name_contains or raise limit when a warning comes back. It also points to meta_list_lead_forms for resolving form IDs. It does not explicitly position itself against meta_ad_performance or meta_ad_preview, so it stops short of a 5.

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