Run a report and return its rows

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Changes nothing in the account' is partly redundant, but the description adds real behavior the annotations cannot: it blocks and polls with progress updates, has configurable timeout/poll defaults, and returns a token on timeout for later retrieval. It also flags semantic traps (SPEND_IN_DOLLAR is account currency despite the name; _1 metrics are paid, _2 earned; HOUR granularity drops conversion metrics).

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 first paragraph is front-loaded and tight, covering mechanics and sibling routing in three sentences. The second block is dense but each clause carries distinct operational information; the only inefficiency is that the level/columns discussion reads as an unstructured run-on rather than being split by parameter domain.

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, so return-value shape need not be described, and the description stays focused on what is uniquely risky for this tool: async polling, timeout recovery, template re-runs, and metric naming pitfalls. For a report-generation tool with 18 params, the async/timeout contract and column semantics are the details an agent would most likely get wrong, and both are covered.

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 it handles about half the 18 parameters well: level values, granularity values, date format, filters structure, report_format, template_id, and the three polling/limit params with defaults. However, ad_account_id, reporting_timezone, conversion_report_time, and the four window_days params receive no explanation anywhere, leaving a caller to guess at attribution semantics that materially change report output.

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?

Specific verb+resource: 'Request a report, wait for it with progress updates, and return its rows.' It distinguishes itself from the four sibling report tools by describing the create-plus-poll-plus-return behavior, and by explicitly deferring to pinterest_ads_create_report, pinterest_ads_get_report and pinterest_ads_list_report_templates for the pieces it does not do itself.

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?

Names alternatives and the conditions that select them: same args as create_report, use get_report to check later after a timeout, use list_report_templates when re-running a saved Ads Manager report via template_id, and list_metrics to resolve column definitions. It also states the targeting_types requirement for *_TARGETING levels, which is a genuine precondition.

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