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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'Read-only' is consistent with that rather than adding new safety information. It does add real behavioral context: the response is a *condensed* summary with a frozen channel/destination set, and drillDown widgets are not expanded here. Minor gap in that it says nothing about payload size limits or what happens if the execution id no longer exists.

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-loaded with the primary purpose, then the id-sourcing hint, then the sibling handoff, then a usage example — a sensible ordering. The dense telegraphic phrasing ('frozen channel and destinations', 'pass returnImage there') is efficient but occasionally terse enough to cost a beat of parsing.

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?

Since there is no output schema, the description properly carries the return-shape burden by enumerating the summary fields, and it closes the main workflow gap by naming the widget sibling for deeper data. It is nearly complete for this complexity level, with only the optional slug/auto-detect behavior left to the schema.

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 100%, and the schema already documents alertId as the cost alert id and executionId as a firing row's messageExecutionId, so the description largely restates it. The only additive element is the worked example object showing both ids together, which does not explain the optional slug parameter or the multi-org failure mode.

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 verb and resource ('get a condensed summary of one alert message run') and immediately enumerates the payload: status, frozen channel/destinations, scheduling timestamps, and per-widget summaries including the ALERT body. This clearly separates it from get_alert_message_execution_widget, which is named as the deeper per-widget fetch.

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?

Explains how to source executionId ('from a firing row's messageExecutionId in get, or list runs via the API') and explicitly routes the agent to get_alert_message_execution_widget when widgets expose drillDown, including the returnImage note for GRAPH_SNAPSHOT PNGs. It even supplies a concrete call example.

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