mlflow_runs_search

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

The description does not contradict the readOnlyHint annotation, but it also adds no additional behavioral context (e.g., side effects, authentication, rate limits). The transparent behavior is adequately covered by the annotation.

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 extremely brief (two short sentences) but sacrifices usefulness for brevity. It lacks structure and does not earn its place by providing actionable information.

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 complexity of searching runs with six parameters (including filters, pagination, ordering) and an output schema, the description is woefully incomplete. It provides no information on usage, return format, or important constraints.

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 description provides no explanation of any parameters. With only 17% schema description coverage, the burden falls entirely on the description, which entirely fails to add meaning beyond parameter names and types.

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 'Search runs' with an API endpoint, clearly identifying the verb and resource. However, it lacks differentiation from sibling tools like mlflow_runs_get, which also retrieves runs. The generic 'search' doesn't explain the scope or unique aspects of this tool.

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 guidance is provided on when to use this tool versus alternatives like mlflow_runs_get or how filtering/pagination works. The agent must infer usage solely 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.