mlflow_runs_log_metric

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

The description discloses that this is a write operation ('log'), which aligns with annotations (readOnlyHint=false). However, it does not go beyond the annotations to disclose other behaviors such as authentication requirements, rate limits, success/error responses, or side effects (e.g., overwriting existing metrics). The output schema exists but is not referenced. The description carries a low burden due to annotations but adds no extra transparency.

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 immediately conveys the tool's purpose. It is front-loaded with the action and includes the endpoint for context. No superfluous words or redundant information. Every part earns its place.

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 the tool has 5 parameters (3 required) and an output schema, the description is too brief. It does not explain the concept of logging metrics in MLflow (e.g., association with runs, use of step/timestamp), nor does it hint at the return value. For a tool with moderate complexity, the description lacks essential context that the agent would need to use it 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?

The input schema already provides descriptions for 4 out of 5 parameters (80% coverage), so the description does not need to repeat them. However, the 'step' parameter lacks a description in both the schema and the tool description, and the tool description does not clarify its usage (e.g., optional step for metric recording). The description adds no additional semantic value beyond the schema, resulting in a baseline score of 3.

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 'Log a single metric', with a specific verb ('log') and resource ('metric'). It also includes the REST endpoint URL for reference. This distinguishes it from sibling tools like mlflow_runs_log_batch (which logs multiple metrics) and mlflow_runs_log_param (which logs a parameter). The purpose is unambiguous.

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 implicitly suggests usage for logging a single metric, but it does not provide explicit guidance on when to use this tool versus alternatives (e.g., mlflow_runs_log_batch for batch operations). No when-not-to-use scenarios or prerequisites are mentioned. The guidance is minimal and leaves the agent to infer context from the tool name.

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