list-trace-attachments

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

Annotations already declare readOnlyHint=true, indicating safe read. The description adds valuable behavioral context: it is Databricks-specific and will return 404 on OSS. This goes beyond annotations, though it does not detail response format or permissions.

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 with no wasted words. It starts with the action ('List attachments') and immediately adds the constraint about Databricks MLflow. Perfectly concise and well structured.

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?

Despite having no output schema, the description does not explain the return format or what information the list contains. While the tool is simple, the omission of response details limits completeness for an agent. The openWorldHint annotation suggests additional context, but it is not elaborated.

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 100% (traceId described as 'Trace ID'). The description's phrase 'List attachments on a trace' adds minimal additional meaning, as the parameter's purpose is already clear from the schema. Baseline of 3 is appropriate.

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 tool lists attachments on a trace, specifies verb 'List', resource 'attachments', and scope 'on a trace'. It also distinguishes from general use by noting it is Databricks MLflow only, differentiating it from potential siblings.

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 clear context that this tool works only on Databricks MLflow and explicitly warns against using on OSS servers (404). It lacks explicit alternatives, but the sibling set includes 'get-trace-attachment', providing implicit differentiation.

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