compare_runs

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

No annotations are provided, so the description carries the full burden. It usefully discloses non-obvious behavior: the 'lower is better unless the catalogue says otherwise' metric rule, tie handling ('a tie names no best'), and error semantics for unknown run ids, but it omits return format, ordering, or permissions.

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 dense, front-loaded sentences with zero filler; the output description and the tie/error rules each earn their 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?

With no output schema and no annotations, the description still conveys the conceptual return (metrics side by side, best per metric) and key error/tie behavior. For a low-complexity one-parameter tool this is nearly complete, though metric definition depends on the unexplained 'catalogue'.

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% for the single run_ids parameter, so the description must compensate. It names run ids and clarifies that unknown ids are an error, and 'side by side' implies multiple ids, adding some meaning beyond the schema, but it doesn't spell out the array format or the minItems=2 constraint.

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?

States a specific verb (compare) and resource (runs) and describes the output shape: headline metrics side by side plus the best run per metric. It is clearly distinguishable from siblings like get_run or list_runs, though it doesn't name them 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 description implies comparison usage but gives no when-to-use conditions, no prerequisites, and no named alternatives versus siblings such as list_runs or get_run. An agent gets no explicit routing guidance.

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