post_insight_result

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

Annotations indicate readOnlyHint=false (mutation) and destructiveHint=false (not destructive). The description adds context: ownership constraint ('Only insights owned by the 'public-api' source can be managed'), metadata-only scope, and explicit separation from resource results. It doesn't state error handling or idempotency, but with annotations covering safety profile, this is adequate.

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?

Description is three sentences: first states primary use, second defines ownership and scope, third provides alternative. It's front-loaded with the main purpose. Slightly wordy but every sentence earns its place, providing crucial disambiguation. No fluff.

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 12 parameters and 5 required, the description covers the key decision points: ownership, metadata vs resources, status alternation. It doesn't detail all params but schema covers them. No output schema exists, but description doesn't promise return format, which is acceptable. The core behaviors are adequately captured for an agent to invoke correctly.

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%, so parameters are already well-documented. The description adds specific context by listing the metadata fields (title, description, categories, status, remediation links) and mentions 'remplenishment links' (though not a direct param name, it maps to cloudFlowTemplateId or reportUrl). It reinforces that status can be updated but not solely, adding semantic nuance beyond the schema.

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 dual purpose: create a new custom insight or update metadata (title, description, categories, status, remediation links). It explicitly identifies the resource and scope (insights owned by 'public-api' source), distinguishing it from sibling tools like post_insight_resource_results and update_insight_status.

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 begins with 'Use this when...' and explicitly states when not to use it: 'Do NOT use this only to change an insight's status (use update_insight_status).' It also distinguishes from post_insight_resource_results for managing affected resources. Provides clear alternatives and exclusions.

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