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 behavioral burden. It usefully discloses the semantics of the comparison (percentage of 'confidently wrong' vs accuracy, broken out per language), which is real behavioral context, but says nothing about read-only nature, permissions, cost of aggregating multiple runs, or failure modes for invalid run IDs.

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?

Front-loaded one-sentence summary followed by a short Args block, with little waste. The Args entry is nearly redundant with its own wording ('the runs to compare'), but it does document the only parameter where the schema has no descriptions.

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?

An output schema exists, so the description is not obliged to explain return values, and it already hints at the compared metrics. For a single-parameter tool this is nearly complete; what is missing is any note on run comparability (e.g. same dataset/model) or behavior on invalid IDs.

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. 'run_ids: the runs to compare' tells the agent to pass run identifiers and that plural runs are expected, but adds no format, count limits, or ordering semantics beyond the schema's array-of-strings definition.

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?

Specific verb (compare) plus resource (runs) and even names the outputs computed (confidently-wrong % and accuracy % per language). The phrase 'for several runs (e.g. different models)' implicitly separates it from the single-run siblings like get_report and run_status, but no sibling is named 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?

Usage is implied rather than stated: the agent can infer this is the tool to reach for when more than one run exists. There is no explicit when-to-use/when-not guidance and no named alternative versus get_report or export_run.

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