List ads

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description earns credit for adding behavior not in structured fields: the schema default for statuses is null but the description reveals the effective default of ACTIVE+PAUSED, that IDs are matched in any status, the max_results output cap, and that summary_status signals actual delivery. It does not discuss pagination or ordering, which would have pushed it higher.

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 compact and front-loaded with purpose before filters, and every clause adds information. It is somewhat telegraphic ("plus ad_group_ids, campaign_ids where supported"), which costs a little readability, but there is no filler.

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 an output schema present, return values need no explanation, and the description covers nearly all six parameters plus the important status default. The one notable omission is the role and optionality of ad_account_id on a tool where no parameter is required, which leaves ambiguity about whether the account must be supplied.

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 0%, so the description carries the full burden and largely succeeds: it explains ids (up to 250), ad_group_ids, campaign_ids, statuses semantics with concrete example values, and max_results. The gaps are ad_account_id (only implied by "in an ad account") and the vague "where supported" caveat on campaign_ids.

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 opens with a specific verb+resource ("List ads in an ad account") and the filter list makes clear it is a filtered read operation, distinguishing it from siblings like pinterest_ads_create_ads or pinterest_ads_archive_ads by implication. It never names a sibling explicitly, so the differentiation is inferential rather than stated.

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?

It gives useful in-tool guidance: the status filter defaults to ACTIVE and PAUSED, and passing ['ARCHIVED'] or ['ALL'] widens it. However, it offers nothing on when to choose this tool over pinterest_ads_list_ad_groups, pinterest_ads_get_analytics, or pinterest_ads_list_metrics for ad-level data, and no prerequisites or exclusions are stated.

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