Get Active Advisor Recommendations for Account

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

The description adds context beyond the annotations (readOnlyHint=true, etc.) by explaining that the tool retrieves active recommendations that help identify issues affecting system availability, stability, performance, or security, and that higher impact/likelihood values indicate more critical issues. It also demonstrates typical usage patterns via examples. No contradiction with annotations is present.

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 relatively concise, starting with a clear purpose sentence followed by a brief overview of filters and numerous call examples. The examples are well-organized but somewhat lengthy. The structure is effective, though the examples could be trimmed or moved into a separate documentation section.

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?

Given that an output schema exists (not shown but stated 'Has output schema: true'), the description does not need to explain return values. It covers the tool's purpose, filter capabilities, and provides usage examples covering pagination, common filters, and sorting. The examples imply pagination and case usage. Minor gaps include no explicit mention of default sorting or the list nature of the response, but the examples compensate.

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?

The input schema has 100% description coverage for all 12 parameters, each with explicit descriptions. The description adds some value by providing specific call examples that show parameter usage (e.g., 'impact': '3,4', 'tags': ['insights-client/group=database-servers']). However, it does not significantly deepen semantic understanding beyond what the schema already provides.

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 states the verb 'Get' and the resource 'active Advisor Recommendations for your account', and explains what these recommendations help identify (system availability, stability, performance, or security). It distinguishes from sibling tools like advisor__get_hosts_details_for_rule or advisor__get_recommendations_stats by focusing on active recommendations with user-controllable filtering, not host details or statistics.

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 description provides numerous call examples that implicitly illustrate when to use various filters (e.g., for high risk, pagination, automatic remediation, security categories). However, it lacks explicit guidance on when to use this tool versus sibling tools, such as advisor__get_rule_details or advisor__get_rule_by_text_search. The verb 'Get' and the mention of filters imply retrieval, but no direct comparison to alternatives is given.

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