List Ads

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

Annotations indicate readOnlyHint=true and destructiveHint=false, which aligns with the 'Lists' verb. The description adds behavioral context beyond annotations by detailing pagination (limit, after) and status_filter options. No contradictions are present, and the description provides useful information for expected behavior.

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?

The description is relatively short and front-loaded with the main purpose. The argument list is structured as a bullet-like list, making it easy to parse. Every sentence adds value, though there is minor redundancy in the first sentence. Overall, it is efficient but not perfectly concise.

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?

The description covers the tool's operation well, including filtering and pagination. However, there is no output schema, and the description does not explain the return format (e.g., what fields each ad includes). Since the tool is read-only and returns a list, some output details would improve completeness. The description is adequate but not fully comprehensive.

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?

The input schema has low description coverage (14%), with only response_format described. The description compensates fully by explaining the meaning of each parameter: adset_id (filter by ad set), campaign_id (filter by campaign), ad_account_id (list all ads in account), status_filter (with enum values), limit (max results default 20), after (pagination cursor). It also clarifies the requirement to provide one of the first three parameters, adding critical context.

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?

The description clearly states 'Lists ads for an ad set, campaign, or ad account.' This is a specific verb+resource combination. It distinguishes itself from siblings like meta_get_ad (single ad) and meta_list_adsets (ad sets) by specifying the parent entities it can filter by. The description also lists filter parameters, reinforcing its purpose.

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?

The description provides clear context by explaining the available filters (adset_id, campaign_id, ad_account_id) and requires one of them. However, it does not explicitly state when not to use this tool or mention alternative tools for similar tasks (e.g., meta_get_ad for a single ad). This limits the guidance for an AI agent to choose between tools.

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