tool_compare_runs

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

No annotations are provided, so the description carries full burden. It mentions what gets compared but doesn't disclose behavioral traits like whether this is a read-only operation, what format the comparison output takes (e.g., table, summary), error handling for invalid log files, or performance considerations. The description is functional but lacks transparency about how the tool behaves beyond its basic function.

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 well-structured and appropriately sized. It starts with a clear purpose statement, follows with specific comparison details, and ends with parameter explanations. Every sentence adds value with no redundancy or fluff, making it easy to scan and understand quickly.

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's moderate complexity (comparing runs with 3 parameters) and lack of annotations/output schema, the description is partially complete. It covers the purpose and parameters well but misses behavioral details (e.g., output format, error handling) and usage guidelines relative to siblings. For a tool without structured metadata, it should do more to compensate, leaving gaps in completeness.

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 0%, so the description must compensate. It provides clear semantics for all three parameters: log_file_a and log_file_b as paths to log files, and log_dir as an optional directory for relative paths. This adds meaningful context beyond the schema's basic string types, explaining what each parameter represents and their relationships (e.g., log_dir applies to both files).

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's purpose: 'Compare metrics between two evaluation runs' with specific details about what gets compared (task/model info, sample counts, score differences, etc.). It uses a specific verb ('compare') and identifies the resource ('evaluation runs'), but doesn't explicitly differentiate from sibling tools like tool_get_aggregate_stats or tool_get_eval_summary that might also involve evaluation data.

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 no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like tool_get_aggregate_stats or tool_get_eval_summary, nor does it specify prerequisites (e.g., that log files must exist from previous runs). The context is implied (comparing two runs) but lacks explicit when/when-not instructions.

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