advance_service_case_resolution

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

Annotations indicate destructive=true and idempotent=false, so the caller knows it is a mutating, non-idempotent action. The description adds that at most one phase is advanced, but it does not explain side effects, failure conditions, or how the three refs are used.

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 a single sentence that is concise and to the point, with the key action placed upfront. It lacks detail, but it is not padded or redundant.

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 tool is a mutating action with three unexplained parameters and no guidance on preconditions or consequences. While an output schema exists, the description still fails to provide enough context for safe or correct invocation.

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 schema provides no descriptions for company_ref, project_ref, or run_ref, and the description does not clarify their meaning or relationships. The caller is left to infer what each reference identifies.

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 states the verb 'advance' and the resource 'service case resolution', which distinguishes it from the sibling start/get/cancel tools. However, the phrase 'approval/effect/observation phase' is ambiguous and does not clearly define what advancing means or what the phase types are.

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?

No explicit guidance is provided about when to use this tool versus starting, getting, or canceling a service case resolution. The 'at most one' hint suggests a constraint but does not clarify the intended invocation context.

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