calc_stats

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

With no annotations, the description must disclose behavioral aspects. It mentions the CV threshold for comparing across runs, which is a useful behavioral note, but it fails to describe input expectations (e.g., must be non-empty), output format, or edge cases. The description is too sparse for a tool with no other metadata.

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 brief, with the first sentence listing the statistics and the second providing a practical interpretation of CV. It is concise and to the point, though the second sentence could be seen as extra usage context rather than core purpose. There is no wasted wording.

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?

For a tool with a single parameter and no output schema, the description should clarify what input is expected and what the return value looks like. The description only lists outputs and gives a CV interpretation, but it does not explain the input array, nor any edge cases (e.g., empty array, single element). It is incomplete for reliable usage.

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 schema has only one parameter (nums), and the description does not mention it at all. Schema description coverage is 0%, so the description should explain what 'nums' expects, but it does not. This is a severe gap; the parameter semantics are not clarified at all.

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 lists the statistics computed (mean, median, sample stdev, CV), making the purpose evident. It does not explicitly use a verb like 'calculate', but the context is unambiguous. It distinguishes from sibling tools like percentiles by listing its specific outputs, though it does not name alternatives.

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 on when to use this tool versus alternatives is provided. The CV interpretation gives some practical context for interpreting results, but it does not suggest use cases or exclude other tools. There are no explicit instructions on prerequisites or typical scenarios.

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