Request an ads report

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Changes nothing in the account' while adding behavior annotations cannot express: the report is built in the background and requires polling plus a token handoff. It also discloses temporal quirks such as HOUR granularity no longer including conversion metrics, and warns that campaign_objective_types should include SALES and LEADS rather than the retiring values.

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 workflow and the 'changes nothing' reassurance are front-loaded, and the parameter guidance is grouped sensibly (level → dates → granularity → filters → format → template). The long column glossary is genuinely useful for choosing report columns, though it is dense enough to make the description read as a wall of text.

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?

For an async report-creation tool with 15 parameters and an output schema, the description covers the lifecycle, the sibling handoffs, the level/granularity/format choices, and common column semantics. Attribution-window parameters are the only notable omission, and the pointer to pinterest_ads_list_metrics for full column definitions closes the other documentation loop.

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%, so the description carries the full burden, and it does substantial work: valid level values, the ≤5 targeting_types link to *_TARGETING levels, date format YYYY-MM-DD, granularity enum, the shape of filters with concrete campaign_ids/campaign_statuses examples, report_format JSON/CSV, and template_id semantics. Six parameters remain unexplained — ad_account_id, view_window_days, click_window_days, engagement_window_days, reporting_timezone, and conversion_report_time — which is the main gap for a 15-parameter tool.

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 ('Request an ads report') and immediately scopes it as an async job rather than an inline result. It distinguishes itself from pinterest_ads_get_report, pinterest_ads_download_report, and pinterest_ads_run_report by naming them and their roles, so an agent can place this tool in a workflow without opening any schema.

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 an explicit decision path: call this, poll pinterest_ads_get_report with the returned token, then pinterest_ads_download_report — or use pinterest_ads_run_report to collapse all three. It also names an alternative mode (template_id for saved Ads Manager reports, with a pointer to pinterest_ads_list_report_templates) and the constraints on that mode (dates and granularity only).

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