compare_runs

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

Annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds a performance caveat about large runs, which is useful behavioral context beyond the annotations.

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?

Two concise sentences with no filler; the key action and a critical warning are front-loaded. Every word serves a purpose.

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 description hints at output ('full metrics and params') but does not fully describe return values or behavior. With no output schema and missing parameter details, the description is adequate but not comprehensive for a tool with two required parameters.

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 coverage is 0%, so the description must compensate. It mentions 'full metrics and params' but does not explain the role of 'experiment_id' or 'run_ids', nor their formats. The warning about keeping the list short hints at run_ids but lacks clarity.

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') and resource ('runs') and adds 'side-by-side with full metrics and params', which clearly distinguishes it from siblings like 'get_run' (single run) or 'query_runs' (search).

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 a clear performance warning: 'Runs can be large — keep the list short.' This guides the agent on best practices. However, it does not explicitly mention when to use alternatives or when not to use the tool.

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