compare_model_runs

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It tells the agent the core behavior is comparing metrics from MLflow runs, which suggests an analytic, non-mutating operation, but it does not disclose the output format, potential side effects, permission concerns, or error behavior around invalid run IDs.

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 front-loaded sentence with no filler. Every phrase contributes meaning: the operation ('Compare'), the data ('metrics'), the objects ('multiple MLflow runs'), and the purpose ('evaluate model performance').

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 single parameter is fully covered by schema and the description provides a clear scenario for use, so an agent can call the tool without missing inputs. However, no output schema exists and the description does not specify what the comparison result will contain or how it will be presented, leaving an important knowledge gap for an agent that needs to interpret the response.

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 already documents 'runIds' with the description 'Array of run IDs to compare', so the schema coverage is 100%. The tool description adds value by clarifying these are MLflow runs and that multiple runs are expected, but it does not specify ID format, limits, or how many runs are valid beyond the implied 'multiple'.

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 uses a specific verb ('Compare'), names a resource type ('metrics between multiple MLflow runs'), and gives an explicit purpose ('evaluate model performance'). This lets an agent distinguish it from retrieval-focused siblings like get_mlflow_runs, though it does not name a sibling explicitly.

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 'to evaluate model performance' clause gives a clear evaluative context, implying this tool is used for run comparison rather than listing or retrieving runs. However, it does not state explicit exclusions or reference alternative tools such as get_mlflow_runs, get_pipeline_runs, or compare_moles, so the agent must infer when the tool is the best choice.

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