audit_portfolio

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower, and the description adds real behavioral value beyond them: it promises partial-failure reporting ('plus the properties that failed and why'), which tells the agent to expect per-property error entries rather than an all-or-nothing failure. It does not mention rate limits or cost of fanning out across many properties.

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?

Front-loads the purpose in the first line and keeps the returns list tight. The 'Args:' block is minimal and not wasteful, though it slightly duplicates the one parameter already named in prose.

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 explaining return fields is arguably redundant, and the description wisely focuses its extra words on failure reporting. However, with 0% schema coverage the undocumented date range parameters leave the agent guessing about the time window, which is material for a metrics tool.

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 must carry the parameter burden, but it only addresses property_ids (giving an example ID format). The date_start and date_end parameters — including their defaults of '7daysAgo'/'today' and accepted date syntax — are never mentioned, leaving a real gap.

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?

States a specific capability: batched summary metrics across multiple GA4 properties, enumerating the metrics returned (sessions, active users, conversions, bounce rate, avg session duration). This implicitly differentiates it from single-property siblings like run_report or get_property, though it never names those alternatives explicitly.

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 phrase 'in one call' and the plural 'several GA4 properties' imply this is the batch option, but there is no explicit when-to-use/when-not statement or comparison to run_report/conversions_summary. Usage must be inferred from the metric list and plural framing.

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