run_report

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

With no annotations provided, the description carries the full burden and handles it well: it discloses that Summary aggregation raises InvalidTimePeriodColumnForSummaryReport when TimePeriod is present, constrains days to 7/14/30, requires start_date/end_date to be provided together or not at all, and notes there is no length restriction (live-verified with a 106-day pull). Return format and auth are not disclosed, but the failure-mode and constraint disclosures are substantive.

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 dense and technical but every sentence carries a constraint or rule — no filler. Purpose is front-loaded before parameter details. It is longer than minimal, but the length is justified by genuinely non-obvious constraints that an agent cannot infer from the schema.

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 a 6-parameter tool with no annotations and no output schema, this is fairly complete: it explains the tricky validation rules, date-mode options, and the expected report_type format. The main gap is the return value shape, which is unforthcoming (no output schema). Given the complexity, it covers the critical calling constraints well even though output format is unaddressed.

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 must compensate, and it does for most parameters: report_type (exact v13 request type, example given), aggregation (default and validity rules), days (allowed values 7/14/30), and start/end_date (format, pairing requirement, no length limit). Only 'columns' is left implicit, but it is largely self-evident and referenced via 'column set' and the TimePeriod exclusion rule.

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 'Arbitrary report (replaces Google run_gaql for metrics pulls)', which names a specific verb, resource, and scope. It clearly distinguishes this generic metrics-report tool from the sibling-specific performance tools (get_campaign_performance, get_ad_performance) by positioning it as the arbitrary/flexible report option.

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 context by naming the legacy tool it replaces (run_gaql) and implicitly frames itself as the generic metrics pull. However, it never explicitly states when to prefer this over sibling performance tools or what conditions would point elsewhere. The strong conditional parameter guidance (Daily vs Summary, days vs start/end_date) is about constructing the call, not tool selection.

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