ga4_run_realtime_report

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

With no annotations, the description carries the full behavioral disclosure burden. It does well by warning about minutes-scale ingestion latency and explicitly stating that an empty result is not proof of data loss, which prevents a common misinterpretation. It does not cover output format, authentication, or quota behavior, but the most operationally important behavior is disclosed.

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: one direct statement of purpose, a minimal request-shape snippet, and a clearly separated IMPORTANT warning. Every sentence earns its place, and the pointer to docs/GA4-LATENCY.md is a useful escape hatch without bloating the description.

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?

The description gives enough to invoke the tool correctly for the required parameters and warns about the most dangerous false-negative trap. But with no output schema, it does not describe what the response looks like, or clarify the optional connection_id and session_token parameters. It is adequate but leaves notable gaps.

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 compensate. It adds essential meaning to the 'report' parameter by showing dimensions and metrics arrays with name fields, which is valuable given the schema treats it as a generic object. However, property_id, connection_id, and session_token receive no additional guidance, and the report shape itself is only partially illustrated with '...'.

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 clearly identifies a specific action and resource: 'Run a GA4 realtime report' and labels it 'read-only'. It also gives a compact request shape for the report object. It does not explicitly name ga4_run_report as the non-realtime alternative, so sibling differentiation relies on the 'realtime' term rather than an explicit contrast.

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 provides an important usage caveat: realtime ingestion latency can produce empty results, and the agent should wait at least 5 minutes or calibrate with a canary before concluding events were dropped. However, it does not explicitly say when to choose this tool over ga4_run_report or when not to use it; the selection guidance is only implied by the word 'realtime'.

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